Skills

---
name: skill-creator
description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
license: Complete terms in LICENSE.txt
---

# Skill Creator

This skill provides guidance for creating effective skills.

## About Skills

Skills are modular, self-contained packages that extend Claude's capabilities by providing
specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
domains or tasks—they transform Claude from a general-purpose agent into a specialized agent
equipped with procedural knowledge that no model can fully possess.

### What Skills Provide

1. Specialized workflows - Multi-step procedures for specific domains
2. Tool integrations - Instructions for working with specific file formats or APIs
3. Domain expertise - Company-specific knowledge, schemas, business logic
4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks

## Core Principles

### Concise is Key

The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.

**Default assumption: Claude is already very smart.** Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"

Prefer concise examples over verbose explanations.

### Set Appropriate Degrees of Freedom

Match the level of specificity to the task's fragility and variability:

**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.

**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.

**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.

Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).

### Anatomy of a Skill

Every skill consists of a required SKILL.md file and optional bundled resources:

```
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

#### SKILL.md (required)

Every SKILL.md consists of:

- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).

#### Bundled Resources (optional)

##### Scripts (`scripts/`)

Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.

- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed
- **Example**: `scripts/rotate_pdf.py` for PDF rotation tasks
- **Benefits**: Token efficient, deterministic, may be executed without loading into context
- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments

##### References (`references/`)

Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.

- **When to include**: For documentation that Claude should reference while working
- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications
- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
- **Benefits**: Keeps SKILL.md lean, loaded only when Claude determines it's needed
- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md
- **Avoid duplication**: Information should live in either SKILL.md or references files, not both.

##### Assets (`assets/`)

Files not intended to be loaded into context, but rather used within the output Claude produces.

- **When to include**: When the skill needs files that will be used in the final output
- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates
- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents

### Progressive Disclosure Design Principle

Skills use a three-level loading system to manage context efficiently:

1. **Metadata (name + description)** - Always in context (~100 words)
2. **SKILL.md body** - When skill triggers (<5k words)
3. **Bundled resources** - As needed by Claude

Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat.

## Skill Creation Process

Skill creation involves these steps:

1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Package the skill (run package_skill.py)
6. Iterate based on real usage

### Step 3: Initializing the Skill

When creating a new skill from scratch, always run the `init_skill.py` script:

```bash
scripts/init_skill.py <skill-name> --path <output-directory>
```

### Step 4: Edit the Skill

Consult these helpful guides based on your skill's needs:

- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic
- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns

### Step 5: Packaging a Skill

```bash
scripts/package_skill.py <path/to/skill-folder>
```

The packaging script validates and creates a .skill file for distribution.
FILE:references/workflows.md
# Workflow Patterns

## Sequential Workflows

For complex tasks, break operations into clear, sequential steps. It is often helpful to give Claude an overview of the process towards the beginning of SKILL.md:

```markdown
Filling a PDF form involves these steps:

1. Analyze the form (run analyze_form.py)
2. Create field mapping (edit fields.json)
3. Validate mapping (run validate_fields.py)
4. Fill the form (run fill_form.py)
5. Verify output (run verify_output.py)
```

## Conditional Workflows

For tasks with branching logic, guide Claude through decision points:

```markdown
1. Determine the modification type:
   **Creating new content?** → Follow "Creation workflow" below
   **Editing existing content?** → Follow "Editing workflow" below

2. Creation workflow: [steps]
3. Editing workflow: [steps]
```
FILE:references/output-patterns.md
# Output Patterns

Use these patterns when skills need to produce consistent, high-quality output.

## Template Pattern

Provide templates for output format. Match the level of strictness to your needs.

**For strict requirements (like API responses or data formats):**

```markdown
## Report structure

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary
[One-paragraph overview of key findings]

## Key findings
- Finding 1 with supporting data
- Finding 2 with supporting data
- Finding 3 with supporting data

## Recommendations
1. Specific actionable recommendation
2. Specific actionable recommendation
```

**For flexible guidance (when adaptation is useful):**

```markdown
## Report structure

Here is a sensible default format, but use your best judgment:

# [Analysis Title]

## Executive summary
[Overview]

## Key findings
[Adapt sections based on what you discover]

## Recommendations
[Tailor to the specific context]

Adjust sections as needed for the specific analysis type.
```

## Examples Pattern

For skills where output quality depends on seeing examples, provide input/output pairs:

```markdown
## Commit message format

Generate commit messages following these examples:

**Example 1:**
Input: Added user authentication with JWT tokens
Output:
```
feat(auth): implement JWT-based authentication

Add login endpoint and token validation middleware
```

**Example 2:**
Input: Fixed bug where dates displayed incorrectly in reports
Output:
```
fix(reports): correct date formatting in timezone conversion

Use UTC timestamps consistently across report generation
```

Follow this style: type(scope): brief description, then detailed explanation.
```

Examples help Claude understand the desired style and level of detail more clearly than descriptions alone.
FILE:scripts/quick_validate.py
#!/usr/bin/env python3
"""
Quick validation script for skills - minimal version
"""

import sys
import os
import re
import yaml
from pathlib import Path

def validate_skill(skill_path):
    """Basic validation of a skill"""
    skill_path = Path(skill_path)

    # Check SKILL.md exists
    skill_md = skill_path / 'SKILL.md'
    if not skill_md.exists():
        return False, "SKILL.md not found"

    # Read and validate frontmatter
    content = skill_md.read_text()
    if not content.startswith('---'):
        return False, "No YAML frontmatter found"

    # Extract frontmatter
    match = re.match(r'^---\n(.*?)\n---', content, re.DOTALL)
    if not match:
        return False, "Invalid frontmatter format"

    frontmatter_text = match.group(1)

    # Parse YAML frontmatter
    try:
        frontmatter = yaml.safe_load(frontmatter_text)
        if not isinstance(frontmatter, dict):
            return False, "Frontmatter must be a YAML dictionary"
    except yaml.YAMLError as e:
        return False, f"Invalid YAML in frontmatter: {e}"

    # Define allowed properties
    ALLOWED_PROPERTIES = {'name', 'description', 'license', 'allowed-tools', 'metadata'}

    # Check for unexpected properties (excluding nested keys under metadata)
    unexpected_keys = set(frontmatter.keys()) - ALLOWED_PROPERTIES
    if unexpected_keys:
        return False, (
            f"Unexpected key(s) in SKILL.md frontmatter: {', '.join(sorted(unexpected_keys))}. "
            f"Allowed properties are: {', '.join(sorted(ALLOWED_PROPERTIES))}"
        )

    # Check required fields
    if 'name' not in frontmatter:
        return False, "Missing 'name' in frontmatter"
    if 'description' not in frontmatter:
        return False, "Missing 'description' in frontmatter"

    # Extract name for validation
    name = frontmatter.get('name', '')
    if not isinstance(name, str):
        return False, f"Name must be a string, got {type(name).__name__}"
    name = name.strip()
    if name:
        # Check naming convention (hyphen-case: lowercase with hyphens)
        if not re.match(r'^[a-z0-9-]+$', name):
            return False, f"Name '{name}' should be hyphen-case (lowercase letters, digits, and hyphens only)"
        if name.startswith('-') or name.endswith('-') or '--' in name:
            return False, f"Name '{name}' cannot start/end with hyphen or contain consecutive hyphens"
        # Check name length (max 64 characters per spec)
        if len(name) > 64:
            return False, f"Name is too long ({len(name)} characters). Maximum is 64 characters."

    # Extract and validate description
    description = frontmatter.get('description', '')
    if not isinstance(description, str):
        return False, f"Description must be a string, got {type(description).__name__}"
    description = description.strip()
    if description:
        # Check for angle brackets
        if '<' in description or '>' in description:
            return False, "Description cannot contain angle brackets (< or >)"
        # Check description length (max 1024 characters per spec)
        if len(description) > 1024:
            return False, f"Description is too long ({len(description)} characters). Maximum is 1024 characters."

    return True, "Skill is valid!"

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python quick_validate.py <skill_directory>")
        sys.exit(1)
    
    valid, message = validate_skill(sys.argv[1])
    print(message)
    sys.exit(0 if valid else 1)
FILE:scripts/init_skill.py
#!/usr/bin/env python3
"""
Skill Initializer - Creates a new skill from template

Usage:
    init_skill.py <skill-name> --path <path>

Examples:
    init_skill.py my-new-skill --path skills/public
    init_skill.py my-api-helper --path skills/private
    init_skill.py custom-skill --path /custom/location
"""

import sys
from pathlib import Path


SKILL_TEMPLATE = """---
name: {skill_name}
description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
---

# {skill_title}

## Overview

[TODO: 1-2 sentences explaining what this skill enables]

## Resources

This skill includes example resource directories that demonstrate how to organize different types of bundled resources:

### scripts/
Executable code (Python/Bash/etc.) that can be run directly to perform specific operations.

### references/
Documentation and reference material intended to be loaded into context to inform Claude's process and thinking.

### assets/
Files not intended to be loaded into context, but rather used within the output Claude produces.

---

**Any unneeded directories can be deleted.** Not every skill requires all three types of resources.
"""

EXAMPLE_SCRIPT = '''#!/usr/bin/env python3
"""
Example helper script for {skill_name}

This is a placeholder script that can be executed directly.
Replace with actual implementation or delete if not needed.
"""

def main():
    print("This is an example script for {skill_name}")
    # TODO: Add actual script logic here

if __name__ == "__main__":
    main()
'''

EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title}

This is a placeholder for detailed reference documentation.
Replace with actual reference content or delete if not needed.
"""

EXAMPLE_ASSET = """# Example Asset File

This placeholder represents where asset files would be stored.
Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed.
"""


def title_case_skill_name(skill_name):
    """Convert hyphenated skill name to Title Case for display."""
    return ' '.join(word.capitalize() for word in skill_name.split('-'))


def init_skill(skill_name, path):
    """Initialize a new skill directory with template SKILL.md."""
    skill_dir = Path(path).resolve() / skill_name

    if skill_dir.exists():
        print(f"❌ Error: Skill directory already exists: {skill_dir}")
        return None

    try:
        skill_dir.mkdir(parents=True, exist_ok=False)
        print(f"✅ Created skill directory: {skill_dir}")
    except Exception as e:
        print(f"❌ Error creating directory: {e}")
        return None

    skill_title = title_case_skill_name(skill_name)
    skill_content = SKILL_TEMPLATE.format(skill_name=skill_name, skill_title=skill_title)

    skill_md_path = skill_dir / 'SKILL.md'
    try:
        skill_md_path.write_text(skill_content)
        print("✅ Created SKILL.md")
    except Exception as e:
        print(f"❌ Error creating SKILL.md: {e}")
        return None

    try:
        scripts_dir = skill_dir / 'scripts'
        scripts_dir.mkdir(exist_ok=True)
        example_script = scripts_dir / 'example.py'
        example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name))
        example_script.chmod(0o755)
        print("✅ Created scripts/example.py")

        references_dir = skill_dir / 'references'
        references_dir.mkdir(exist_ok=True)
        example_reference = references_dir / 'api_reference.md'
        example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title))
        print("✅ Created references/api_reference.md")

        assets_dir = skill_dir / 'assets'
        assets_dir.mkdir(exist_ok=True)
        example_asset = assets_dir / 'example_asset.txt'
        example_asset.write_text(EXAMPLE_ASSET)
        print("✅ Created assets/example_asset.txt")
    except Exception as e:
        print(f"❌ Error creating resource directories: {e}")
        return None

    print(f"\n✅ Skill '{skill_name}' initialized successfully at {skill_dir}")
    return skill_dir


def main():
    if len(sys.argv) < 4 or sys.argv[2] != '--path':
        print("Usage: init_skill.py <skill-name> --path <path>")
        sys.exit(1)

    skill_name = sys.argv[1]
    path = sys.argv[3]

    print(f"🚀 Initializing skill: {skill_name}")
    print(f"   Location: {path}")
    print()

    result = init_skill(skill_name, path)
    sys.exit(0 if result else 1)


if __name__ == "__main__":
    main()
FILE:scripts/package_skill.py
#!/usr/bin/env python3
"""
Skill Packager - Creates a distributable .skill file of a skill folder

Usage:
    python utils/package_skill.py <path/to/skill-folder> [output-directory]

Example:
    python utils/package_skill.py skills/public/my-skill
    python utils/package_skill.py skills/public/my-skill ./dist
"""

import sys
import zipfile
from pathlib import Path
from quick_validate import validate_skill


def package_skill(skill_path, output_dir=None):
    """Package a skill folder into a .skill file."""
    skill_path = Path(skill_path).resolve()

    if not skill_path.exists():
        print(f"❌ Error: Skill folder not found: {skill_path}")
        return None

    if not skill_path.is_dir():
        print(f"❌ Error: Path is not a directory: {skill_path}")
        return None

    skill_md = skill_path / "SKILL.md"
    if not skill_md.exists():
        print(f"❌ Error: SKILL.md not found in {skill_path}")
        return None

    print("🔍 Validating skill...")
    valid, message = validate_skill(skill_path)
    if not valid:
        print(f"❌ Validation failed: {message}")
        print("   Please fix the validation errors before packaging.")
        return None
    print(f"✅ {message}\n")

    skill_name = skill_path.name
    if output_dir:
        output_path = Path(output_dir).resolve()
        output_path.mkdir(parents=True, exist_ok=True)
    else:
        output_path = Path.cwd()

    skill_filename = output_path / f"{skill_name}.skill"

    try:
        with zipfile.ZipFile(skill_filename, 'w', zipfile.ZIP_DEFLATED) as zipf:
            for file_path in skill_path.rglob('*'):
                if file_path.is_file():
                    arcname = file_path.relative_to(skill_path.parent)
                    zipf.write(file_path, arcname)
                    print(f"  Added: {arcname}")

        print(f"\n✅ Successfully packaged skill to: {skill_filename}")
        return skill_filename

    except Exception as e:
        print(f"❌ Error creating .skill file: {e}")
        return None


def main():
    if len(sys.argv) < 2:
        print("Usage: python utils/package_skill.py <path/to/skill-folder> [output-directory]")
        sys.exit(1)

    skill_path = sys.argv[1]
    output_dir = sys.argv[2] if len(sys.argv) > 2 else None

    print(f"📦 Packaging skill: {skill_path}")
    if output_dir:
        print(f"   Output directory: {output_dir}")
    print()

    result = package_skill(skill_path, output_dir)
    sys.exit(0 if result else 1)


if __name__ == "__main__":
    main()

---
name: mcp-builder
description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
license: Complete terms in LICENSE.txt
---

# MCP Server Development Guide

## Overview

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

---

# Process

## 🚀 High-Level Workflow

Creating a high-quality MCP server involves four main phases:

### Phase 1: Deep Research and Planning

#### 1.1 Understand Modern MCP Design

**API Coverage vs. Workflow Tools:**
Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.

**Tool Naming and Discoverability:**
Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming.

**Context Management:**
Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.

**Actionable Error Messages:**
Error messages should guide agents toward solutions with specific suggestions and next steps.

#### 1.2 Study MCP Protocol Documentation

**Navigate the MCP specification:**

Start with the sitemap to find relevant pages: `https://modelcontextprotocol.io/sitemap.xml`

Then fetch specific pages with `.md` suffix for markdown format (e.g., `https://modelcontextprotocol.io/specification/draft.md`).

Key pages to review:
- Specification overview and architecture
- Transport mechanisms (streamable HTTP, stdio)
- Tool, resource, and prompt definitions

#### 1.3 Study Framework Documentation

**Recommended stack:**
- **Language**: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)
- **Transport**: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.

**Load framework documentation:**

- **MCP Best Practices**: [📋 View Best Practices](./reference/mcp_best_practices.md) - Core guidelines

**For TypeScript (recommended):**
- **TypeScript SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`
- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - TypeScript patterns and examples

**For Python:**
- **Python SDK**: Use WebFetch to load `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
- [🐍 Python Guide](./reference/python_mcp_server.md) - Python patterns and examples

#### 1.4 Plan Your Implementation

**Understand the API:**
Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.

**Tool Selection:**
Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.

---

### Phase 2: Implementation

#### 2.1 Set Up Project Structure

See language-specific guides for project setup:
- [⚡ TypeScript Guide](./reference/node_mcp_server.md) - Project structure, package.json, tsconfig.json
- [🐍 Python Guide](./reference/python_mcp_server.md) - Module organization, dependencies

#### 2.2 Implement Core Infrastructure

Create shared utilities:
- API client with authentication
- Error handling helpers
- Response formatting (JSON/Markdown)
- Pagination support

#### 2.3 Implement Tools

For each tool:

**Input Schema:**
- Use Zod (TypeScript) or Pydantic (Python)
- Include constraints and clear descriptions
- Add examples in field descriptions

**Output Schema:**
- Define `outputSchema` where possible for structured data
- Use `structuredContent` in tool responses (TypeScript SDK feature)
- Helps clients understand and process tool outputs

**Tool Description:**
- Concise summary of functionality
- Parameter descriptions
- Return type schema

**Implementation:**
- Async/await for I/O operations
- Proper error handling with actionable messages
- Support pagination where applicable
- Return both text content and structured data when using modern SDKs

**Annotations:**
- `readOnlyHint`: true/false
- `destructiveHint`: true/false
- `idempotentHint`: true/false
- `openWorldHint`: true/false

---

### Phase 3: Review and Test

#### 3.1 Code Quality

Review for:
- No duplicated code (DRY principle)
- Consistent error handling
- Full type coverage
- Clear tool descriptions

#### 3.2 Build and Test

**TypeScript:**
- Run `npm run build` to verify compilation
- Test with MCP Inspector: `npx @modelcontextprotocol/inspector`

**Python:**
- Verify syntax: `python -m py_compile your_server.py`
- Test with MCP Inspector

See language-specific guides for detailed testing approaches and quality checklists.

---

### Phase 4: Create Evaluations

After implementing your MCP server, create comprehensive evaluations to test its effectiveness.

**Load [✅ Evaluation Guide](./reference/evaluation.md) for complete evaluation guidelines.**

#### 4.1 Understand Evaluation Purpose

Use evaluations to test whether LLMs can effectively use your MCP server to answer realistic, complex questions.

#### 4.2 Create 10 Evaluation Questions

To create effective evaluations, follow the process outlined in the evaluation guide:

1. **Tool Inspection**: List available tools and understand their capabilities
2. **Content Exploration**: Use READ-ONLY operations to explore available data
3. **Question Generation**: Create 10 complex, realistic questions
4. **Answer Verification**: Solve each question yourself to verify answers

#### 4.3 Evaluation Requirements

Ensure each question is:
- **Independent**: Not dependent on other questions
- **Read-only**: Only non-destructive operations required
- **Complex**: Requiring multiple tool calls and deep exploration
- **Realistic**: Based on real use cases humans would care about
- **Verifiable**: Single, clear answer that can be verified by string comparison
- **Stable**: Answer won't change over time

#### 4.4 Output Format

Create an XML file with this structure:

```xml
<evaluation>
  <qa_pair>
    <question>Find discussions about AI model launches with animal codenames. One model needed a specific safety designation that uses the format ASL-X. What number X was being determined for the model named after a spotted wild cat?</question>
    <answer>3</answer>
  </qa_pair>
<!-- More qa_pairs... -->
</evaluation>
```

---

# Reference Files

## 📚 Documentation Library

Load these resources as needed during development:

### Core MCP Documentation (Load First)
- **MCP Protocol**: Start with sitemap at `https://modelcontextprotocol.io/sitemap.xml`, then fetch specific pages with `.md` suffix
- [📋 MCP Best Practices](./reference/mcp_best_practices.md) - Universal MCP guidelines including:
  - Server and tool naming conventions
  - Response format guidelines (JSON vs Markdown)
  - Pagination best practices
  - Transport selection (streamable HTTP vs stdio)
  - Security and error handling standards

### SDK Documentation (Load During Phase 1/2)
- **Python SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`
- **TypeScript SDK**: Fetch from `https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md`

### Language-Specific Implementation Guides (Load During Phase 2)
- [🐍 Python Implementation Guide](./reference/python_mcp_server.md) - Complete Python/FastMCP guide with:
  - Server initialization patterns
  - Pydantic model examples
  - Tool registration with `@mcp.tool`
  - Complete working examples
  - Quality checklist

- [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md) - Complete TypeScript guide with:
  - Project structure
  - Zod schema patterns
  - Tool registration with `server.registerTool`
  - Complete working examples
  - Quality checklist

### Evaluation Guide (Load During Phase 4)
- [✅ Evaluation Guide](./reference/evaluation.md) - Complete evaluation creation guide with:
  - Question creation guidelines
  - Answer verification strategies
  - XML format specifications
  - Example questions and answers
  - Running an evaluation with the provided scripts
FILE:reference/mcp_best_practices.md
# MCP Server Best Practices

## Quick Reference

### Server Naming
- **Python**: `{service}_mcp` (e.g., `slack_mcp`)
- **Node/TypeScript**: `{service}-mcp-server` (e.g., `slack-mcp-server`)

### Tool Naming
- Use snake_case with service prefix
- Format: `{service}_{action}_{resource}`
- Example: `slack_send_message`, `github_create_issue`

### Response Formats
- Support both JSON and Markdown formats
- JSON for programmatic processing
- Markdown for human readability

### Pagination
- Always respect `limit` parameter
- Return `has_more`, `next_offset`, `total_count`
- Default to 20-50 items

### Transport
- **Streamable HTTP**: For remote servers, multi-client scenarios
- **stdio**: For local integrations, command-line tools
- Avoid SSE (deprecated in favor of streamable HTTP)

---

## Server Naming Conventions

Follow these standardized naming patterns:

**Python**: Use format `{service}_mcp` (lowercase with underscores)
- Examples: `slack_mcp`, `github_mcp`, `jira_mcp`

**Node/TypeScript**: Use format `{service}-mcp-server` (lowercase with hyphens)
- Examples: `slack-mcp-server`, `github-mcp-server`, `jira-mcp-server`

The name should be general, descriptive of the service being integrated, easy to infer from the task description, and without version numbers.

---

## Tool Naming and Design

### Tool Naming

1. **Use snake_case**: `search_users`, `create_project`, `get_channel_info`
2. **Include service prefix**: Anticipate that your MCP server may be used alongside other MCP servers
   - Use `slack_send_message` instead of just `send_message`
   - Use `github_create_issue` instead of just `create_issue`
3. **Be action-oriented**: Start with verbs (get, list, search, create, etc.)
4. **Be specific**: Avoid generic names that could conflict with other servers

### Tool Design

- Tool descriptions must narrowly and unambiguously describe functionality
- Descriptions must precisely match actual functionality
- Provide tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- Keep tool operations focused and atomic

---

## Response Formats

All tools that return data should support multiple formats:

### JSON Format (`response_format="json"`)
- Machine-readable structured data
- Include all available fields and metadata
- Consistent field names and types
- Use for programmatic processing

### Markdown Format (`response_format="markdown"`, typically default)
- Human-readable formatted text
- Use headers, lists, and formatting for clarity
- Convert timestamps to human-readable format
- Show display names with IDs in parentheses
- Omit verbose metadata

---

## Pagination

For tools that list resources:

- **Always respect the `limit` parameter**
- **Implement pagination**: Use `offset` or cursor-based pagination
- **Return pagination metadata**: Include `has_more`, `next_offset`/`next_cursor`, `total_count`
- **Never load all results into memory**: Especially important for large datasets
- **Default to reasonable limits**: 20-50 items is typical

Example pagination response:
```json
{
  "total": 150,
  "count": 20,
  "offset": 0,
  "items": [...],
  "has_more": true,
  "next_offset": 20
}
```

---

## Transport Options

### Streamable HTTP

**Best for**: Remote servers, web services, multi-client scenarios

**Characteristics**:
- Bidirectional communication over HTTP
- Supports multiple simultaneous clients
- Can be deployed as a web service
- Enables server-to-client notifications

**Use when**:
- Serving multiple clients simultaneously
- Deploying as a cloud service
- Integration with web applications

### stdio

**Best for**: Local integrations, command-line tools

**Characteristics**:
- Standard input/output stream communication
- Simple setup, no network configuration needed
- Runs as a subprocess of the client

**Use when**:
- Building tools for local development environments
- Integrating with desktop applications
- Single-user, single-session scenarios

**Note**: stdio servers should NOT log to stdout (use stderr for logging)

### Transport Selection

| Criterion | stdio | Streamable HTTP |
|-----------|-------|-----------------|
| **Deployment** | Local | Remote |
| **Clients** | Single | Multiple |
| **Complexity** | Low | Medium |
| **Real-time** | No | Yes |

---

## Security Best Practices

### Authentication and Authorization

**OAuth 2.1**:
- Use secure OAuth 2.1 with certificates from recognized authorities
- Validate access tokens before processing requests
- Only accept tokens specifically intended for your server

**API Keys**:
- Store API keys in environment variables, never in code
- Validate keys on server startup
- Provide clear error messages when authentication fails

### Input Validation

- Sanitize file paths to prevent directory traversal
- Validate URLs and external identifiers
- Check parameter sizes and ranges
- Prevent command injection in system calls
- Use schema validation (Pydantic/Zod) for all inputs

### Error Handling

- Don't expose internal errors to clients
- Log security-relevant errors server-side
- Provide helpful but not revealing error messages
- Clean up resources after errors

### DNS Rebinding Protection

For streamable HTTP servers running locally:
- Enable DNS rebinding protection
- Validate the `Origin` header on all incoming connections
- Bind to `127.0.0.1` rather than `0.0.0.0`

---

## Tool Annotations

Provide annotations to help clients understand tool behavior:

| Annotation | Type | Default | Description |
|-----------|------|---------|-------------|
| `readOnlyHint` | boolean | false | Tool does not modify its environment |
| `destructiveHint` | boolean | true | Tool may perform destructive updates |
| `idempotentHint` | boolean | false | Repeated calls with same args have no additional effect |
| `openWorldHint` | boolean | true | Tool interacts with external entities |

**Important**: Annotations are hints, not security guarantees. Clients should not make security-critical decisions based solely on annotations.

---

## Error Handling

- Use standard JSON-RPC error codes
- Report tool errors within result objects (not protocol-level errors)
- Provide helpful, specific error messages with suggested next steps
- Don't expose internal implementation details
- Clean up resources properly on errors

Example error handling:
```typescript
try {
  const result = performOperation();
  return { content: [{ type: "text", text: result }] };
} catch (error) {
  return {
    isError: true,
    content: [{
      type: "text",
      text: `Error: error.message. Try using filter='active_only' to reduce results.`
    }]
  };
}
```

---

## Testing Requirements

Comprehensive testing should cover:

- **Functional testing**: Verify correct execution with valid/invalid inputs
- **Integration testing**: Test interaction with external systems
- **Security testing**: Validate auth, input sanitization, rate limiting
- **Performance testing**: Check behavior under load, timeouts
- **Error handling**: Ensure proper error reporting and cleanup

---

## Documentation Requirements

- Provide clear documentation of all tools and capabilities
- Include working examples (at least 3 per major feature)
- Document security considerations
- Specify required permissions and access levels
- Document rate limits and performance characteristics
FILE:reference/evaluation.md
# MCP Server Evaluation Guide

## Overview

This document provides guidance on creating comprehensive evaluations for MCP servers. Evaluations test whether LLMs can effectively use your MCP server to answer realistic, complex questions using only the tools provided.

---

## Quick Reference

### Evaluation Requirements
- Create 10 human-readable questions
- Questions must be READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE
- Each question requires multiple tool calls (potentially dozens)
- Answers must be single, verifiable values
- Answers must be STABLE (won't change over time)

### Output Format
```xml
<evaluation>
   <qa_pair>
      <question>Your question here</question>
      <answer>Single verifiable answer</answer>
   </qa_pair>
</evaluation>
```

---

## Purpose of Evaluations

The measure of quality of an MCP server is NOT how well or comprehensively the server implements tools, but how well these implementations (input/output schemas, docstrings/descriptions, functionality) enable LLMs with no other context and access ONLY to the MCP servers to answer realistic and difficult questions.

## Evaluation Overview

Create 10 human-readable questions requiring ONLY READ-ONLY, INDEPENDENT, NON-DESTRUCTIVE, and IDEMPOTENT operations to answer. Each question should be:
- Realistic
- Clear and concise
- Unambiguous
- Complex, requiring potentially dozens of tool calls or steps
- Answerable with a single, verifiable value that you identify in advance

## Question Guidelines

### Core Requirements

1. **Questions MUST be independent**
   - Each question should NOT depend on the answer to any other question
   - Should not assume prior write operations from processing another question

2. **Questions MUST require ONLY NON-DESTRUCTIVE AND IDEMPOTENT tool use**
   - Should not instruct or require modifying state to arrive at the correct answer

3. **Questions must be REALISTIC, CLEAR, CONCISE, and COMPLEX**
   - Must require another LLM to use multiple (potentially dozens of) tools or steps to answer

### Complexity and Depth

4. **Questions must require deep exploration**
   - Consider multi-hop questions requiring multiple sub-questions and sequential tool calls
   - Each step should benefit from information found in previous questions

5. **Questions may require extensive paging**
   - May need paging through multiple pages of results
   - May require querying old data (1-2 years out-of-date) to find niche information
   - The questions must be DIFFICULT

6. **Questions must require deep understanding**
   - Rather than surface-level knowledge
   - May pose complex ideas as True/False questions requiring evidence
   - May use multiple-choice format where LLM must search different hypotheses

7. **Questions must not be solvable with straightforward keyword search**
   - Do not include specific keywords from the target content
   - Use synonyms, related concepts, or paraphrases
   - Require multiple searches, analyzing multiple related items, extracting context, then deriving the answer

### Tool Testing

8. **Questions should stress-test tool return values**
   - May elicit tools returning large JSON objects or lists, overwhelming the LLM
   - Should require understanding multiple modalities of data:
     - IDs and names
     - Timestamps and datetimes (months, days, years, seconds)
     - File IDs, names, extensions, and mimetypes
     - URLs, GIDs, etc.
   - Should probe the tool's ability to return all useful forms of data

9. **Questions should MOSTLY reflect real human use cases**
   - The kinds of information retrieval tasks that HUMANS assisted by an LLM would care about

10. **Questions may require dozens of tool calls**
    - This challenges LLMs with limited context
    - Encourages MCP server tools to reduce information returned

11. **Include ambiguous questions**
    - May be ambiguous OR require difficult decisions on which tools to call
    - Force the LLM to potentially make mistakes or misinterpret
    - Ensure that despite AMBIGUITY, there is STILL A SINGLE VERIFIABLE ANSWER

### Stability

12. **Questions must be designed so the answer DOES NOT CHANGE**
    - Do not ask questions that rely on "current state" which is dynamic
    - For example, do not count:
      - Number of reactions to a post
      - Number of replies to a thread
      - Number of members in a channel

13. **DO NOT let the MCP server RESTRICT the kinds of questions you create**
    - Create challenging and complex questions
    - Some may not be solvable with the available MCP server tools
    - Questions may require specific output formats (datetime vs. epoch time, JSON vs. MARKDOWN)
    - Questions may require dozens of tool calls to complete

## Answer Guidelines

### Verification

1. **Answers must be VERIFIABLE via direct string comparison**
   - If the answer can be re-written in many formats, clearly specify the output format in the QUESTION
   - Examples: "Use YYYY/MM/DD.", "Respond True or False.", "Answer A, B, C, or D and nothing else."
   - Answer should be a single VERIFIABLE value such as:
     - User ID, user name, display name, first name, last name
     - Channel ID, channel name
     - Message ID, string
     - URL, title
     - Numerical quantity
     - Timestamp, datetime
     - Boolean (for True/False questions)
     - Email address, phone number
     - File ID, file name, file extension
     - Multiple choice answer
   - Answers must not require special formatting or complex, structured output
   - Answer will be verified using DIRECT STRING COMPARISON

### Readability

2. **Answers should generally prefer HUMAN-READABLE formats**
   - Examples: names, first name, last name, datetime, file name, message string, URL, yes/no, true/false, a/b/c/d
   - Rather than opaque IDs (though IDs are acceptable)
   - The VAST MAJORITY of answers should be human-readable

### Stability

3. **Answers must be STABLE/STATIONARY**
   - Look at old content (e.g., conversations that have ended, projects that have launched, questions answered)
   - Create QUESTIONS based on "closed" concepts that will always return the same answer
   - Questions may ask to consider a fixed time window to insulate from non-stationary answers
   - Rely on context UNLIKELY to change
   - Example: if finding a paper name, be SPECIFIC enough so answer is not confused with papers published later

4. **Answers must be CLEAR and UNAMBIGUOUS**
   - Questions must be designed so there is a single, clear answer
   - Answer can be derived from using the MCP server tools

### Diversity

5. **Answers must be DIVERSE**
   - Answer should be a single VERIFIABLE value in diverse modalities and formats
   - User concept: user ID, user name, display name, first name, last name, email address, phone number
   - Channel concept: channel ID, channel name, channel topic
   - Message concept: message ID, message string, timestamp, month, day, year

6. **Answers must NOT be complex structures**
   - Not a list of values
   - Not a complex object
   - Not a list of IDs or strings
   - Not natural language text
   - UNLESS the answer can be straightforwardly verified using DIRECT STRING COMPARISON
   - And can be realistically reproduced
   - It should be unlikely that an LLM would return the same list in any other order or format

## Evaluation Process

### Step 1: Documentation Inspection

Read the documentation of the target API to understand:
- Available endpoints and functionality
- If ambiguity exists, fetch additional information from the web
- Parallelize this step AS MUCH AS POSSIBLE
- Ensure each subagent is ONLY examining documentation from the file system or on the web

### Step 2: Tool Inspection

List the tools available in the MCP server:
- Inspect the MCP server directly
- Understand input/output schemas, docstrings, and descriptions
- WITHOUT calling the tools themselves at this stage

### Step 3: Developing Understanding

Repeat steps 1 & 2 until you have a good understanding:
- Iterate multiple times
- Think about the kinds of tasks you want to create
- Refine your understanding
- At NO stage should you READ the code of the MCP server implementation itself
- Use your intuition and understanding to create reasonable, realistic, but VERY challenging tasks

### Step 4: Read-Only Content Inspection

After understanding the API and tools, USE the MCP server tools:
- Inspect content using READ-ONLY and NON-DESTRUCTIVE operations ONLY
- Goal: identify specific content (e.g., users, channels, messages, projects, tasks) for creating realistic questions
- Should NOT call any tools that modify state
- Will NOT read the code of the MCP server implementation itself
- Parallelize this step with individual sub-agents pursuing independent explorations
- Ensure each subagent is only performing READ-ONLY, NON-DESTRUCTIVE, and IDEMPOTENT operations
- BE CAREFUL: SOME TOOLS may return LOTS OF DATA which would cause you to run out of CONTEXT
- Make INCREMENTAL, SMALL, AND TARGETED tool calls for exploration
- In all tool call requests, use the `limit` parameter to limit results (<10)
- Use pagination

### Step 5: Task Generation

After inspecting the content, create 10 human-readable questions:
- An LLM should be able to answer these with the MCP server
- Follow all question and answer guidelines above

## Output Format

Each QA pair consists of a question and an answer. The output should be an XML file with this structure:

```xml
<evaluation>
   <qa_pair>
      <question>Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name?</question>
      <answer>Website Redesign</answer>
   </qa_pair>
   <qa_pair>
      <question>Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username.</question>
      <answer>sarah_dev</answer>
   </qa_pair>
   <qa_pair>
      <question>Look for pull requests that modified files in the /api directory and were merged between January 1 and January 31, 2024. How many different contributors worked on these PRs?</question>
      <answer>7</answer>
   </qa_pair>
   <qa_pair>
      <question>Find the repository with the most stars that was created before 2023. What is the repository name?</question>
      <answer>data-pipeline</answer>
   </qa_pair>
</evaluation>
```

## Evaluation Examples

### Good Questions

**Example 1: Multi-hop question requiring deep exploration (GitHub MCP)**
```xml
<qa_pair>
   <question>Find the repository that was archived in Q3 2023 and had previously been the most forked project in the organization. What was the primary programming language used in that repository?</question>
   <answer>Python</answer>
</qa_pair>
```

This question is good because:
- Requires multiple searches to find archived repositories
- Needs to identify which had the most forks before archival
- Requires examining repository details for the language
- Answer is a simple, verifiable value
- Based on historical (closed) data that won't change

**Example 2: Requires understanding context without keyword matching (Project Management MCP)**
```xml
<qa_pair>
   <question>Locate the initiative focused on improving customer onboarding that was completed in late 2023. The project lead created a retrospective document after completion. What was the lead's role title at that time?</question>
   <answer>Product Manager</answer>
</qa_pair>
```

This question is good because:
- Doesn't use specific project name ("initiative focused on improving customer onboarding")
- Requires finding completed projects from specific timeframe
- Needs to identify the project lead and their role
- Requires understanding context from retrospective documents
- Answer is human-readable and stable
- Based on completed work (won't change)

**Example 3: Complex aggregation requiring multiple steps (Issue Tracker MCP)**
```xml
<qa_pair>
   <question>Among all bugs reported in January 2024 that were marked as critical priority, which assignee resolved the highest percentage of their assigned bugs within 48 hours? Provide the assignee's username.</question>
   <answer>alex_eng</answer>
</qa_pair>
```

This question is good because:
- Requires filtering bugs by date, priority, and status
- Needs to group by assignee and calculate resolution rates
- Requires understanding timestamps to determine 48-hour windows
- Tests pagination (potentially many bugs to process)
- Answer is a single username
- Based on historical data from specific time period

**Example 4: Requires synthesis across multiple data types (CRM MCP)**
```xml
<qa_pair>
   <question>Find the account that upgraded from the Starter to Enterprise plan in Q4 2023 and had the highest annual contract value. What industry does this account operate in?</question>
   <answer>Healthcare</answer>
</qa_pair>
```

This question is good because:
- Requires understanding subscription tier changes
- Needs to identify upgrade events in specific timeframe
- Requires comparing contract values
- Must access account industry information
- Answer is simple and verifiable
- Based on completed historical transactions

### Poor Questions

**Example 1: Answer changes over time**
```xml
<qa_pair>
   <question>How many open issues are currently assigned to the engineering team?</question>
   <answer>47</answer>
</qa_pair>
```

This question is poor because:
- The answer will change as issues are created, closed, or reassigned
- Not based on stable/stationary data
- Relies on "current state" which is dynamic

**Example 2: Too easy with keyword search**
```xml
<qa_pair>
   <question>Find the pull request with title "Add authentication feature" and tell me who created it.</question>
   <answer>developer123</answer>
</qa_pair>
```

This question is poor because:
- Can be solved with a straightforward keyword search for exact title
- Doesn't require deep exploration or understanding
- No synthesis or analysis needed

**Example 3: Ambiguous answer format**
```xml
<qa_pair>
   <question>List all the repositories that have Python as their primary language.</question>
   <answer>repo1, repo2, repo3, data-pipeline, ml-tools</answer>
</qa_pair>
```

This question is poor because:
- Answer is a list that could be returned in any order
- Difficult to verify with direct string comparison
- LLM might format differently (JSON array, comma-separated, newline-separated)
- Better to ask for a specific aggregate (count) or superlative (most stars)

## Verification Process

After creating evaluations:

1. **Examine the XML file** to understand the schema
2. **Load each task instruction** and in parallel using the MCP server and tools, identify the correct answer by attempting to solve the task YOURSELF
3. **Flag any operations** that require WRITE or DESTRUCTIVE operations
4. **Accumulate all CORRECT answers** and replace any incorrect answers in the document
5. **Remove any `<qa_pair>`** that require WRITE or DESTRUCTIVE operations

Remember to parallelize solving tasks to avoid running out of context, then accumulate all answers and make changes to the file at the end.

## Tips for Creating Quality Evaluations

1. **Think Hard and Plan Ahead** before generating tasks
2. **Parallelize Where Opportunity Arises** to speed up the process and manage context
3. **Focus on Realistic Use Cases** that humans would actually want to accomplish
4. **Create Challenging Questions** that test the limits of the MCP server's capabilities
5. **Ensure Stability** by using historical data and closed concepts
6. **Verify Answers** by solving the questions yourself using the MCP server tools
7. **Iterate and Refine** based on what you learn during the process

---

# Running Evaluations

After creating your evaluation file, you can use the provided evaluation harness to test your MCP server.

## Setup

1. **Install Dependencies**

   ```bash
   pip install -r scripts/requirements.txt
   ```

   Or install manually:
   ```bash
   pip install anthropic mcp
   ```

2. **Set API Key**

   ```bash
   export ANTHROPIC_API_KEY=your_api_key_here
   ```

## Evaluation File Format

Evaluation files use XML format with `<qa_pair>` elements:

```xml
<evaluation>
   <qa_pair>
      <question>Find the project created in Q2 2024 with the highest number of completed tasks. What is the project name?</question>
      <answer>Website Redesign</answer>
   </qa_pair>
   <qa_pair>
      <question>Search for issues labeled as "bug" that were closed in March 2024. Which user closed the most issues? Provide their username.</question>
      <answer>sarah_dev</answer>
   </qa_pair>
</evaluation>
```

## Running Evaluations

The evaluation script (`scripts/evaluation.py`) supports three transport types:

**Important:**
- **stdio transport**: The evaluation script automatically launches and manages the MCP server process for you. Do not run the server manually.
- **sse/http transports**: You must start the MCP server separately before running the evaluation. The script connects to the already-running server at the specified URL.

### 1. Local STDIO Server

For locally-run MCP servers (script launches the server automatically):

```bash
python scripts/evaluation.py \
  -t stdio \
  -c python \
  -a my_mcp_server.py \
  evaluation.xml
```

With environment variables:
```bash
python scripts/evaluation.py \
  -t stdio \
  -c python \
  -a my_mcp_server.py \
  -e API_KEY=abc123 \
  -e DEBUG=true \
  evaluation.xml
```

### 2. Server-Sent Events (SSE)

For SSE-based MCP servers (you must start the server first):

```bash
python scripts/evaluation.py \
  -t sse \
  -u https://example.com/mcp \
  -H "Authorization: Bearer token123" \
  -H "X-Custom-Header: value" \
  evaluation.xml
```

### 3. HTTP (Streamable HTTP)

For HTTP-based MCP servers (you must start the server first):

```bash
python scripts/evaluation.py \
  -t http \
  -u https://example.com/mcp \
  -H "Authorization: Bearer token123" \
  evaluation.xml
```

## Command-Line Options

```
usage: evaluation.py [-h] [-t {stdio,sse,http}] [-m MODEL] [-c COMMAND]
                     [-a ARGS [ARGS ...]] [-e ENV [ENV ...]] [-u URL]
                     [-H HEADERS [HEADERS ...]] [-o OUTPUT]
                     eval_file

positional arguments:
  eval_file             Path to evaluation XML file

optional arguments:
  -h, --help            Show help message
  -t, --transport       Transport type: stdio, sse, or http (default: stdio)
  -m, --model           Claude model to use (default: claude-3-7-sonnet-20250219)
  -o, --output          Output file for report (default: print to stdout)

stdio options:
  -c, --command         Command to run MCP server (e.g., python, node)
  -a, --args            Arguments for the command (e.g., server.py)
  -e, --env             Environment variables in KEY=VALUE format

sse/http options:
  -u, --url             MCP server URL
  -H, --header          HTTP headers in 'Key: Value' format
```

## Output

The evaluation script generates a detailed report including:

- **Summary Statistics**:
  - Accuracy (correct/total)
  - Average task duration
  - Average tool calls per task
  - Total tool calls

- **Per-Task Results**:
  - Prompt and expected response
  - Actual response from the agent
  - Whether the answer was correct (✅/❌)
  - Duration and tool call details
  - Agent's summary of its approach
  - Agent's feedback on the tools

### Save Report to File

```bash
python scripts/evaluation.py \
  -t stdio \
  -c python \
  -a my_server.py \
  -o evaluation_report.md \
  evaluation.xml
```

## Complete Example Workflow

Here's a complete example of creating and running an evaluation:

1. **Create your evaluation file** (`my_evaluation.xml`):

```xml
<evaluation>
   <qa_pair>
      <question>Find the user who created the most issues in January 2024. What is their username?</question>
      <answer>alice_developer</answer>
   </qa_pair>
   <qa_pair>
      <question>Among all pull requests merged in Q1 2024, which repository had the highest number? Provide the repository name.</question>
      <answer>backend-api</answer>
   </qa_pair>
   <qa_pair>
      <question>Find the project that was completed in December 2023 and had the longest duration from start to finish. How many days did it take?</question>
      <answer>127</answer>
   </qa_pair>
</evaluation>
```

2. **Install dependencies**:

```bash
pip install -r scripts/requirements.txt
export ANTHROPIC_API_KEY=your_api_key
```

3. **Run evaluation**:

```bash
python scripts/evaluation.py \
  -t stdio \
  -c python \
  -a github_mcp_server.py \
  -e GITHUB_TOKEN=ghp_xxx \
  -o github_eval_report.md \
  my_evaluation.xml
```

4. **Review the report** in `github_eval_report.md` to:
   - See which questions passed/failed
   - Read the agent's feedback on your tools
   - Identify areas for improvement
   - Iterate on your MCP server design

## Troubleshooting

### Connection Errors

If you get connection errors:
- **STDIO**: Verify the command and arguments are correct
- **SSE/HTTP**: Check the URL is accessible and headers are correct
- Ensure any required API keys are set in environment variables or headers

### Low Accuracy

If many evaluations fail:
- Review the agent's feedback for each task
- Check if tool descriptions are clear and comprehensive
- Verify input parameters are well-documented
- Consider whether tools return too much or too little data
- Ensure error messages are actionable

### Timeout Issues

If tasks are timing out:
- Use a more capable model (e.g., `claude-3-7-sonnet-20250219`)
- Check if tools are returning too much data
- Verify pagination is working correctly
- Consider simplifying complex questions
FILE:reference/node_mcp_server.md
# Node/TypeScript MCP Server Implementation Guide

## Overview

This document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK. It covers project structure, server setup, tool registration patterns, input validation with Zod, error handling, and complete working examples.

---

## Quick Reference

### Key Imports
```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import express from "express";
import { z } from "zod";
```

### Server Initialization
```typescript
const server = new McpServer({
  name: "service-mcp-server",
  version: "1.0.0"
});
```

### Tool Registration Pattern
```typescript
server.registerTool(
  "tool_name",
  {
    title: "Tool Display Name",
    description: "What the tool does",
    inputSchema: { param: z.string() },
    outputSchema: { result: z.string() }
  },
  async ({ param }) => {
    const output = { result: `Processed: param` };
    return {
      content: [{ type: "text", text: JSON.stringify(output) }],
      structuredContent: output // Modern pattern for structured data
    };
  }
);
```

---

## MCP TypeScript SDK

The official MCP TypeScript SDK provides:
- `McpServer` class for server initialization
- `registerTool` method for tool registration
- Zod schema integration for runtime input validation
- Type-safe tool handler implementations

**IMPORTANT - Use Modern APIs Only:**
- **DO use**: `server.registerTool()`, `server.registerResource()`, `server.registerPrompt()`
- **DO NOT use**: Old deprecated APIs such as `server.tool()`, `server.setRequestHandler(ListToolsRequestSchema, ...)`, or manual handler registration
- The `register*` methods provide better type safety, automatic schema handling, and are the recommended approach

See the MCP SDK documentation in the references for complete details.

## Server Naming Convention

Node/TypeScript MCP servers must follow this naming pattern:
- **Format**: `{service}-mcp-server` (lowercase with hyphens)
- **Examples**: `github-mcp-server`, `jira-mcp-server`, `stripe-mcp-server`

The name should be:
- General (not tied to specific features)
- Descriptive of the service/API being integrated
- Easy to infer from the task description
- Without version numbers or dates

## Project Structure

Create the following structure for Node/TypeScript MCP servers:

```
{service}-mcp-server/
├── package.json
├── tsconfig.json
├── README.md
├── src/
│   ├── index.ts          # Main entry point with McpServer initialization
│   ├── types.ts          # TypeScript type definitions and interfaces
│   ├── tools/            # Tool implementations (one file per domain)
│   ├── services/         # API clients and shared utilities
│   ├── schemas/          # Zod validation schemas
│   └── constants.ts      # Shared constants (API_URL, CHARACTER_LIMIT, etc.)
└── dist/                 # Built JavaScript files (entry point: dist/index.js)
```

## Tool Implementation

### Tool Naming

Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names.

**Avoid Naming Conflicts**: Include the service context to prevent overlaps:
- Use "slack_send_message" instead of just "send_message"
- Use "github_create_issue" instead of just "create_issue"
- Use "asana_list_tasks" instead of just "list_tasks"

### Tool Structure

Tools are registered using the `registerTool` method with the following requirements:
- Use Zod schemas for runtime input validation and type safety
- The `description` field must be explicitly provided - JSDoc comments are NOT automatically extracted
- Explicitly provide `title`, `description`, `inputSchema`, and `annotations`
- The `inputSchema` must be a Zod schema object (not a JSON schema)
- Type all parameters and return values explicitly

```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";

const server = new McpServer({
  name: "example-mcp",
  version: "1.0.0"
});

// Zod schema for input validation
const UserSearchInputSchema = z.object({
  query: z.string()
    .min(2, "Query must be at least 2 characters")
    .max(200, "Query must not exceed 200 characters")
    .describe("Search string to match against names/emails"),
  limit: z.number()
    .int()
    .min(1)
    .max(100)
    .default(20)
    .describe("Maximum results to return"),
  offset: z.number()
    .int()
    .min(0)
    .default(0)
    .describe("Number of results to skip for pagination"),
  response_format: z.nativeEnum(ResponseFormat)
    .default(ResponseFormat.MARKDOWN)
    .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable")
}).strict();

// Type definition from Zod schema
type UserSearchInput = z.infer<typeof UserSearchInputSchema>;

server.registerTool(
  "example_search_users",
  {
    title: "Search Example Users",
    description: `Search for users in the Example system by name, email, or team.

This tool searches across all user profiles in the Example platform, supporting partial matches and various search filters. It does NOT create or modify users, only searches existing ones.

Args:
  - query (string): Search string to match against names/emails
  - limit (number): Maximum results to return, between 1-100 (default: 20)
  - offset (number): Number of results to skip for pagination (default: 0)
  - response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns:
  For JSON format: Structured data with schema:
  {
    "total": number,           // Total number of matches found
    "count": number,           // Number of results in this response
    "offset": number,          // Current pagination offset
    "users": [
      {
        "id": string,          // User ID (e.g., "U123456789")
        "name": string,        // Full name (e.g., "John Doe")
        "email": string,       // Email address
        "team": string,        // Team name (optional)
        "active": boolean      // Whether user is active
      }
    ],
    "has_more": boolean,       // Whether more results are available
    "next_offset": number      // Offset for next page (if has_more is true)
  }

Examples:
  - Use when: "Find all marketing team members" -> params with query="team:marketing"
  - Use when: "Search for John's account" -> params with query="john"
  - Don't use when: You need to create a user (use example_create_user instead)

Error Handling:
  - Returns "Error: Rate limit exceeded" if too many requests (429 status)
  - Returns "No users found matching '<query>'" if search returns empty`,
    inputSchema: UserSearchInputSchema,
    annotations: {
      readOnlyHint: true,
      destructiveHint: false,
      idempotentHint: true,
      openWorldHint: true
    }
  },
  async (params: UserSearchInput) => {
    try {
      // Input validation is handled by Zod schema
      // Make API request using validated parameters
      const data = await makeApiRequest<any>(
        "users/search",
        "GET",
        undefined,
        {
          q: params.query,
          limit: params.limit,
          offset: params.offset
        }
      );

      const users = data.users || [];
      const total = data.total || 0;

      if (!users.length) {
        return {
          content: [{
            type: "text",
            text: `No users found matching 'params.query'`
          }]
        };
      }

      // Prepare structured output
      const output = {
        total,
        count: users.length,
        offset: params.offset,
        users: users.map((user: any) => ({
          id: user.id,
          name: user.name,
          email: user.email,
          ...(user.team ? { team: user.team } : {}),
          active: user.active ?? true
        })),
        has_more: total > params.offset + users.length,
        ...(total > params.offset + users.length ? {
          next_offset: params.offset + users.length
        } : {})
      };

      // Format text representation based on requested format
      let textContent: string;
      if (params.response_format === ResponseFormat.MARKDOWN) {
        const lines = [`# User Search Results: 'params.query'`, "",
          `Found total users (showing users.length)`, ""];
        for (const user of users) {
          lines.push(`## user.name (user.id)`);
          lines.push(`- **Email**: user.email`);
          if (user.team) lines.push(`- **Team**: user.team`);
          lines.push("");
        }
        textContent = lines.join("\n");
      } else {
        textContent = JSON.stringify(output, null, 2);
      }

      return {
        content: [{ type: "text", text: textContent }],
        structuredContent: output // Modern pattern for structured data
      };
    } catch (error) {
      return {
        content: [{
          type: "text",
          text: handleApiError(error)
        }]
      };
    }
  }
);
```

## Zod Schemas for Input Validation

Zod provides runtime type validation:

```typescript
import { z } from "zod";

// Basic schema with validation
const CreateUserSchema = z.object({
  name: z.string()
    .min(1, "Name is required")
    .max(100, "Name must not exceed 100 characters"),
  email: z.string()
    .email("Invalid email format"),
  age: z.number()
    .int("Age must be a whole number")
    .min(0, "Age cannot be negative")
    .max(150, "Age cannot be greater than 150")
}).strict();  // Use .strict() to forbid extra fields

// Enums
enum ResponseFormat {
  MARKDOWN = "markdown",
  JSON = "json"
}

const SearchSchema = z.object({
  response_format: z.nativeEnum(ResponseFormat)
    .default(ResponseFormat.MARKDOWN)
    .describe("Output format")
});

// Optional fields with defaults
const PaginationSchema = z.object({
  limit: z.number()
    .int()
    .min(1)
    .max(100)
    .default(20)
    .describe("Maximum results to return"),
  offset: z.number()
    .int()
    .min(0)
    .default(0)
    .describe("Number of results to skip")
});
```

## Response Format Options

Support multiple output formats for flexibility:

```typescript
enum ResponseFormat {
  MARKDOWN = "markdown",
  JSON = "json"
}

const inputSchema = z.object({
  query: z.string(),
  response_format: z.nativeEnum(ResponseFormat)
    .default(ResponseFormat.MARKDOWN)
    .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable")
});
```

**Markdown format**:
- Use headers, lists, and formatting for clarity
- Convert timestamps to human-readable format
- Show display names with IDs in parentheses
- Omit verbose metadata
- Group related information logically

**JSON format**:
- Return complete, structured data suitable for programmatic processing
- Include all available fields and metadata
- Use consistent field names and types

## Pagination Implementation

For tools that list resources:

```typescript
const ListSchema = z.object({
  limit: z.number().int().min(1).max(100).default(20),
  offset: z.number().int().min(0).default(0)
});

async function listItems(params: z.infer<typeof ListSchema>) {
  const data = await apiRequest(params.limit, params.offset);

  const response = {
    total: data.total,
    count: data.items.length,
    offset: params.offset,
    items: data.items,
    has_more: data.total > params.offset + data.items.length,
    next_offset: data.total > params.offset + data.items.length
      ? params.offset + data.items.length
      : undefined
  };

  return JSON.stringify(response, null, 2);
}
```

## Character Limits and Truncation

Add a CHARACTER_LIMIT constant to prevent overwhelming responses:

```typescript
// At module level in constants.ts
export const CHARACTER_LIMIT = 25000;  // Maximum response size in characters

async function searchTool(params: SearchInput) {
  let result = generateResponse(data);

  // Check character limit and truncate if needed
  if (result.length > CHARACTER_LIMIT) {
    const truncatedData = data.slice(0, Math.max(1, data.length / 2));
    response.data = truncatedData;
    response.truncated = true;
    response.truncation_message =
      `Response truncated from data.length to truncatedData.length items. ` +
      `Use 'offset' parameter or add filters to see more results.`;
    result = JSON.stringify(response, null, 2);
  }

  return result;
}
```

## Error Handling

Provide clear, actionable error messages:

```typescript
import axios, { AxiosError } from "axios";

function handleApiError(error: unknown): string {
  if (error instanceof AxiosError) {
    if (error.response) {
      switch (error.response.status) {
        case 404:
          return "Error: Resource not found. Please check the ID is correct.";
        case 403:
          return "Error: Permission denied. You don't have access to this resource.";
        case 429:
          return "Error: Rate limit exceeded. Please wait before making more requests.";
        default:
          return `Error: API request failed with status error.response.status`;
      }
    } else if (error.code === "ECONNABORTED") {
      return "Error: Request timed out. Please try again.";
    }
  }
  return `Error: Unexpected error occurred: String(error)`;
}
```

## Shared Utilities

Extract common functionality into reusable functions:

```typescript
// Shared API request function
async function makeApiRequest<T>(
  endpoint: string,
  method: "GET" | "POST" | "PUT" | "DELETE" = "GET",
  data?: any,
  params?: any
): Promise<T> {
  try {
    const response = await axios({
      method,
      url: `API_BASE_URL/endpoint`,
      data,
      params,
      timeout: 30000,
      headers: {
        "Content-Type": "application/json",
        "Accept": "application/json"
      }
    });
    return response.data;
  } catch (error) {
    throw error;
  }
}
```

## Async/Await Best Practices

Always use async/await for network requests and I/O operations:

```typescript
// Good: Async network request
async function fetchData(resourceId: string): Promise<ResourceData> {
  const response = await axios.get(`API_URL/resource/resourceId`);
  return response.data;
}

// Bad: Promise chains
function fetchData(resourceId: string): Promise<ResourceData> {
  return axios.get(`API_URL/resource/resourceId`)
    .then(response => response.data);  // Harder to read and maintain
}
```

## TypeScript Best Practices

1. **Use Strict TypeScript**: Enable strict mode in tsconfig.json
2. **Define Interfaces**: Create clear interface definitions for all data structures
3. **Avoid `any`**: Use proper types or `unknown` instead of `any`
4. **Zod for Runtime Validation**: Use Zod schemas to validate external data
5. **Type Guards**: Create type guard functions for complex type checking
6. **Error Handling**: Always use try-catch with proper error type checking
7. **Null Safety**: Use optional chaining (`?.`) and nullish coalescing (`??`)

```typescript
// Good: Type-safe with Zod and interfaces
interface UserResponse {
  id: string;
  name: string;
  email: string;
  team?: string;
  active: boolean;
}

const UserSchema = z.object({
  id: z.string(),
  name: z.string(),
  email: z.string().email(),
  team: z.string().optional(),
  active: z.boolean()
});

type User = z.infer<typeof UserSchema>;

async function getUser(id: string): Promise<User> {
  const data = await apiCall(`/users/id`);
  return UserSchema.parse(data);  // Runtime validation
}

// Bad: Using any
async function getUser(id: string): Promise<any> {
  return await apiCall(`/users/id`);  // No type safety
}
```

## Package Configuration

### package.json

```json
{
  "name": "{service}-mcp-server",
  "version": "1.0.0",
  "description": "MCP server for {Service} API integration",
  "type": "module",
  "main": "dist/index.js",
  "scripts": {
    "start": "node dist/index.js",
    "dev": "tsx watch src/index.ts",
    "build": "tsc",
    "clean": "rm -rf dist"
  },
  "engines": {
    "node": ">=18"
  },
  "dependencies": {
    "@modelcontextprotocol/sdk": "^1.6.1",
    "axios": "^1.7.9",
    "zod": "^3.23.8"
  },
  "devDependencies": {
    "@types/node": "^22.10.0",
    "tsx": "^4.19.2",
    "typescript": "^5.7.2"
  }
}
```

### tsconfig.json

```json
{
  "compilerOptions": {
    "target": "ES2022",
    "module": "Node16",
    "moduleResolution": "Node16",
    "lib": ["ES2022"],
    "outDir": "./dist",
    "rootDir": "./src",
    "strict": true,
    "esModuleInterop": true,
    "skipLibCheck": true,
    "forceConsistentCasingInFileNames": true,
    "declaration": true,
    "declarationMap": true,
    "sourceMap": true,
    "allowSyntheticDefaultImports": true
  },
  "include": ["src/**/*"],
  "exclude": ["node_modules", "dist"]
}
```

## Complete Example

```typescript
#!/usr/bin/env node
/**
 * MCP Server for Example Service.
 *
 * This server provides tools to interact with Example API, including user search,
 * project management, and data export capabilities.
 */

import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { z } from "zod";
import axios, { AxiosError } from "axios";

// Constants
const API_BASE_URL = "https://api.example.com/v1";
const CHARACTER_LIMIT = 25000;

// Enums
enum ResponseFormat {
  MARKDOWN = "markdown",
  JSON = "json"
}

// Zod schemas
const UserSearchInputSchema = z.object({
  query: z.string()
    .min(2, "Query must be at least 2 characters")
    .max(200, "Query must not exceed 200 characters")
    .describe("Search string to match against names/emails"),
  limit: z.number()
    .int()
    .min(1)
    .max(100)
    .default(20)
    .describe("Maximum results to return"),
  offset: z.number()
    .int()
    .min(0)
    .default(0)
    .describe("Number of results to skip for pagination"),
  response_format: z.nativeEnum(ResponseFormat)
    .default(ResponseFormat.MARKDOWN)
    .describe("Output format: 'markdown' for human-readable or 'json' for machine-readable")
}).strict();

type UserSearchInput = z.infer<typeof UserSearchInputSchema>;

// Shared utility functions
async function makeApiRequest<T>(
  endpoint: string,
  method: "GET" | "POST" | "PUT" | "DELETE" = "GET",
  data?: any,
  params?: any
): Promise<T> {
  try {
    const response = await axios({
      method,
      url: `API_BASE_URL/endpoint`,
      data,
      params,
      timeout: 30000,
      headers: {
        "Content-Type": "application/json",
        "Accept": "application/json"
      }
    });
    return response.data;
  } catch (error) {
    throw error;
  }
}

function handleApiError(error: unknown): string {
  if (error instanceof AxiosError) {
    if (error.response) {
      switch (error.response.status) {
        case 404:
          return "Error: Resource not found. Please check the ID is correct.";
        case 403:
          return "Error: Permission denied. You don't have access to this resource.";
        case 429:
          return "Error: Rate limit exceeded. Please wait before making more requests.";
        default:
          return `Error: API request failed with status error.response.status`;
      }
    } else if (error.code === "ECONNABORTED") {
      return "Error: Request timed out. Please try again.";
    }
  }
  return `Error: Unexpected error occurred: String(error)`;
}

// Create MCP server instance
const server = new McpServer({
  name: "example-mcp",
  version: "1.0.0"
});

// Register tools
server.registerTool(
  "example_search_users",
  {
    title: "Search Example Users",
    description: `[Full description as shown above]`,
    inputSchema: UserSearchInputSchema,
    annotations: {
      readOnlyHint: true,
      destructiveHint: false,
      idempotentHint: true,
      openWorldHint: true
    }
  },
  async (params: UserSearchInput) => {
    // Implementation as shown above
  }
);

// Main function
// For stdio (local):
async function runStdio() {
  if (!process.env.EXAMPLE_API_KEY) {
    console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
    process.exit(1);
  }

  const transport = new StdioServerTransport();
  await server.connect(transport);
  console.error("MCP server running via stdio");
}

// For streamable HTTP (remote):
async function runHTTP() {
  if (!process.env.EXAMPLE_API_KEY) {
    console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
    process.exit(1);
  }

  const app = express();
  app.use(express.json());

  app.post('/mcp', async (req, res) => {
    const transport = new StreamableHTTPServerTransport({
      sessionIdGenerator: undefined,
      enableJsonResponse: true
    });
    res.on('close', () => transport.close());
    await server.connect(transport);
    await transport.handleRequest(req, res, req.body);
  });

  const port = parseInt(process.env.PORT || '3000');
  app.listen(port, () => {
    console.error(`MCP server running on http://localhost:port/mcp`);
  });
}

// Choose transport based on environment
const transport = process.env.TRANSPORT || 'stdio';
if (transport === 'http') {
  runHTTP().catch(error => {
    console.error("Server error:", error);
    process.exit(1);
  });
} else {
  runStdio().catch(error => {
    console.error("Server error:", error);
    process.exit(1);
  });
}
```

---

## Advanced MCP Features

### Resource Registration

Expose data as resources for efficient, URI-based access:

```typescript
import { ResourceTemplate } from "@modelcontextprotocol/sdk/types.js";

// Register a resource with URI template
server.registerResource(
  {
    uri: "file://documents/{name}",
    name: "Document Resource",
    description: "Access documents by name",
    mimeType: "text/plain"
  },
  async (uri: string) => {
    // Extract parameter from URI
    const match = uri.match(/^file:\/\/documents\/(.+)$/);
    if (!match) {
      throw new Error("Invalid URI format");
    }

    const documentName = match[1];
    const content = await loadDocument(documentName);

    return {
      contents: [{
        uri,
        mimeType: "text/plain",
        text: content
      }]
    };
  }
);

// List available resources dynamically
server.registerResourceList(async () => {
  const documents = await getAvailableDocuments();
  return {
    resources: documents.map(doc => ({
      uri: `file://documents/doc.name`,
      name: doc.name,
      mimeType: "text/plain",
      description: doc.description
    }))
  };
});
```

**When to use Resources vs Tools:**
- **Resources**: For data access with simple URI-based parameters
- **Tools**: For complex operations requiring validation and business logic
- **Resources**: When data is relatively static or template-based
- **Tools**: When operations have side effects or complex workflows

### Transport Options

The TypeScript SDK supports two main transport mechanisms:

#### Streamable HTTP (Recommended for Remote Servers)

```typescript
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
import express from "express";

const app = express();
app.use(express.json());

app.post('/mcp', async (req, res) => {
  // Create new transport for each request (stateless, prevents request ID collisions)
  const transport = new StreamableHTTPServerTransport({
    sessionIdGenerator: undefined,
    enableJsonResponse: true
  });

  res.on('close', () => transport.close());

  await server.connect(transport);
  await transport.handleRequest(req, res, req.body);
});

app.listen(3000);
```

#### stdio (For Local Integrations)

```typescript
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

const transport = new StdioServerTransport();
await server.connect(transport);
```

**Transport selection:**
- **Streamable HTTP**: Web services, remote access, multiple clients
- **stdio**: Command-line tools, local development, subprocess integration

### Notification Support

Notify clients when server state changes:

```typescript
// Notify when tools list changes
server.notification({
  method: "notifications/tools/list_changed"
});

// Notify when resources change
server.notification({
  method: "notifications/resources/list_changed"
});
```

Use notifications sparingly - only when server capabilities genuinely change.

---

## Code Best Practices

### Code Composability and Reusability

Your implementation MUST prioritize composability and code reuse:

1. **Extract Common Functionality**:
   - Create reusable helper functions for operations used across multiple tools
   - Build shared API clients for HTTP requests instead of duplicating code
   - Centralize error handling logic in utility functions
   - Extract business logic into dedicated functions that can be composed
   - Extract shared markdown or JSON field selection & formatting functionality

2. **Avoid Duplication**:
   - NEVER copy-paste similar code between tools
   - If you find yourself writing similar logic twice, extract it into a function
   - Common operations like pagination, filtering, field selection, and formatting should be shared
   - Authentication/authorization logic should be centralized

## Building and Running

Always build your TypeScript code before running:

```bash
# Build the project
npm run build

# Run the server
npm start

# Development with auto-reload
npm run dev
```

Always ensure `npm run build` completes successfully before considering the implementation complete.

## Quality Checklist

Before finalizing your Node/TypeScript MCP server implementation, ensure:

### Strategic Design
- [ ] Tools enable complete workflows, not just API endpoint wrappers
- [ ] Tool names reflect natural task subdivisions
- [ ] Response formats optimize for agent context efficiency
- [ ] Human-readable identifiers used where appropriate
- [ ] Error messages guide agents toward correct usage

### Implementation Quality
- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented
- [ ] All tools registered using `registerTool` with complete configuration
- [ ] All tools include `title`, `description`, `inputSchema`, and `annotations`
- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- [ ] All tools use Zod schemas for runtime input validation with `.strict()` enforcement
- [ ] All Zod schemas have proper constraints and descriptive error messages
- [ ] All tools have comprehensive descriptions with explicit input/output types
- [ ] Descriptions include return value examples and complete schema documentation
- [ ] Error messages are clear, actionable, and educational

### TypeScript Quality
- [ ] TypeScript interfaces are defined for all data structures
- [ ] Strict TypeScript is enabled in tsconfig.json
- [ ] No use of `any` type - use `unknown` or proper types instead
- [ ] All async functions have explicit Promise<T> return types
- [ ] Error handling uses proper type guards (e.g., `axios.isAxiosError`, `z.ZodError`)

### Advanced Features (where applicable)
- [ ] Resources registered for appropriate data endpoints
- [ ] Appropriate transport configured (stdio or streamable HTTP)
- [ ] Notifications implemented for dynamic server capabilities
- [ ] Type-safe with SDK interfaces

### Project Configuration
- [ ] Package.json includes all necessary dependencies
- [ ] Build script produces working JavaScript in dist/ directory
- [ ] Main entry point is properly configured as dist/index.js
- [ ] Server name follows format: `{service}-mcp-server`
- [ ] tsconfig.json properly configured with strict mode

### Code Quality
- [ ] Pagination is properly implemented where applicable
- [ ] Large responses check CHARACTER_LIMIT constant and truncate with clear messages
- [ ] Filtering options are provided for potentially large result sets
- [ ] All network operations handle timeouts and connection errors gracefully
- [ ] Common functionality is extracted into reusable functions
- [ ] Return types are consistent across similar operations

### Testing and Build
- [ ] `npm run build` completes successfully without errors
- [ ] dist/index.js created and executable
- [ ] Server runs: `node dist/index.js --help`
- [ ] All imports resolve correctly
- [ ] Sample tool calls work as expected
FILE:reference/python_mcp_server.md
# Python MCP Server Implementation Guide

## Overview

This document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK. It covers server setup, tool registration patterns, input validation with Pydantic, error handling, and complete working examples.

---

## Quick Reference

### Key Imports
```python
from mcp.server.fastmcp import FastMCP
from pydantic import BaseModel, Field, field_validator, ConfigDict
from typing import Optional, List, Dict, Any
from enum import Enum
import httpx
```

### Server Initialization
```python
mcp = FastMCP("service_mcp")
```

### Tool Registration Pattern
```python
@mcp.tool(name="tool_name", annotations={...})
async def tool_function(params: InputModel) -> str:
    # Implementation
    pass
```

---

## MCP Python SDK and FastMCP

The official MCP Python SDK provides FastMCP, a high-level framework for building MCP servers. It provides:
- Automatic description and inputSchema generation from function signatures and docstrings
- Pydantic model integration for input validation
- Decorator-based tool registration with `@mcp.tool`

**For complete SDK documentation, use WebFetch to load:**
`https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md`

## Server Naming Convention

Python MCP servers must follow this naming pattern:
- **Format**: `{service}_mcp` (lowercase with underscores)
- **Examples**: `github_mcp`, `jira_mcp`, `stripe_mcp`

The name should be:
- General (not tied to specific features)
- Descriptive of the service/API being integrated
- Easy to infer from the task description
- Without version numbers or dates

## Tool Implementation

### Tool Naming

Use snake_case for tool names (e.g., "search_users", "create_project", "get_channel_info") with clear, action-oriented names.

**Avoid Naming Conflicts**: Include the service context to prevent overlaps:
- Use "slack_send_message" instead of just "send_message"
- Use "github_create_issue" instead of just "create_issue"
- Use "asana_list_tasks" instead of just "list_tasks"

### Tool Structure with FastMCP

Tools are defined using the `@mcp.tool` decorator with Pydantic models for input validation:

```python
from pydantic import BaseModel, Field, ConfigDict
from mcp.server.fastmcp import FastMCP

# Initialize the MCP server
mcp = FastMCP("example_mcp")

# Define Pydantic model for input validation
class ServiceToolInput(BaseModel):
    '''Input model for service tool operation.'''
    model_config = ConfigDict(
        str_strip_whitespace=True,  # Auto-strip whitespace from strings
        validate_assignment=True,    # Validate on assignment
        extra='forbid'              # Forbid extra fields
    )

    param1: str = Field(..., description="First parameter description (e.g., 'user123', 'project-abc')", min_length=1, max_length=100)
    param2: Optional[int] = Field(default=None, description="Optional integer parameter with constraints", ge=0, le=1000)
    tags: Optional[List[str]] = Field(default_factory=list, description="List of tags to apply", max_items=10)

@mcp.tool(
    name="service_tool_name",
    annotations={
        "title": "Human-Readable Tool Title",
        "readOnlyHint": True,     # Tool does not modify environment
        "destructiveHint": False,  # Tool does not perform destructive operations
        "idempotentHint": True,    # Repeated calls have no additional effect
        "openWorldHint": False     # Tool does not interact with external entities
    }
)
async def service_tool_name(params: ServiceToolInput) -> str:
    '''Tool description automatically becomes the 'description' field.

    This tool performs a specific operation on the service. It validates all inputs
    using the ServiceToolInput Pydantic model before processing.

    Args:
        params (ServiceToolInput): Validated input parameters containing:
            - param1 (str): First parameter description
            - param2 (Optional[int]): Optional parameter with default
            - tags (Optional[List[str]]): List of tags

    Returns:
        str: JSON-formatted response containing operation results
    '''
    # Implementation here
    pass
```

## Pydantic v2 Key Features

- Use `model_config` instead of nested `Config` class
- Use `field_validator` instead of deprecated `validator`
- Use `model_dump()` instead of deprecated `dict()`
- Validators require `@classmethod` decorator
- Type hints are required for validator methods

```python
from pydantic import BaseModel, Field, field_validator, ConfigDict

class CreateUserInput(BaseModel):
    model_config = ConfigDict(
        str_strip_whitespace=True,
        validate_assignment=True
    )

    name: str = Field(..., description="User's full name", min_length=1, max_length=100)
    email: str = Field(..., description="User's email address", pattern=r'^[\w\.-]+@[\w\.-]+\.\w+$')
    age: int = Field(..., description="User's age", ge=0, le=150)

    @field_validator('email')
    @classmethod
    def validate_email(cls, v: str) -> str:
        if not v.strip():
            raise ValueError("Email cannot be empty")
        return v.lower()
```

## Response Format Options

Support multiple output formats for flexibility:

```python
from enum import Enum

class ResponseFormat(str, Enum):
    '''Output format for tool responses.'''
    MARKDOWN = "markdown"
    JSON = "json"

class UserSearchInput(BaseModel):
    query: str = Field(..., description="Search query")
    response_format: ResponseFormat = Field(
        default=ResponseFormat.MARKDOWN,
        description="Output format: 'markdown' for human-readable or 'json' for machine-readable"
    )
```

**Markdown format**:
- Use headers, lists, and formatting for clarity
- Convert timestamps to human-readable format (e.g., "2024-01-15 10:30:00 UTC" instead of epoch)
- Show display names with IDs in parentheses (e.g., "@john.doe (U123456)")
- Omit verbose metadata (e.g., show only one profile image URL, not all sizes)
- Group related information logically

**JSON format**:
- Return complete, structured data suitable for programmatic processing
- Include all available fields and metadata
- Use consistent field names and types

## Pagination Implementation

For tools that list resources:

```python
class ListInput(BaseModel):
    limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100)
    offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0)

async def list_items(params: ListInput) -> str:
    # Make API request with pagination
    data = await api_request(limit=params.limit, offset=params.offset)

    # Return pagination info
    response = {
        "total": data["total"],
        "count": len(data["items"]),
        "offset": params.offset,
        "items": data["items"],
        "has_more": data["total"] > params.offset + len(data["items"]),
        "next_offset": params.offset + len(data["items"]) if data["total"] > params.offset + len(data["items"]) else None
    }
    return json.dumps(response, indent=2)
```

## Error Handling

Provide clear, actionable error messages:

```python
def _handle_api_error(e: Exception) -> str:
    '''Consistent error formatting across all tools.'''
    if isinstance(e, httpx.HTTPStatusError):
        if e.response.status_code == 404:
            return "Error: Resource not found. Please check the ID is correct."
        elif e.response.status_code == 403:
            return "Error: Permission denied. You don't have access to this resource."
        elif e.response.status_code == 429:
            return "Error: Rate limit exceeded. Please wait before making more requests."
        return f"Error: API request failed with status {e.response.status_code}"
    elif isinstance(e, httpx.TimeoutException):
        return "Error: Request timed out. Please try again."
    return f"Error: Unexpected error occurred: {type(e).__name__}"
```

## Shared Utilities

Extract common functionality into reusable functions:

```python
# Shared API request function
async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict:
    '''Reusable function for all API calls.'''
    async with httpx.AsyncClient() as client:
        response = await client.request(
            method,
            f"{API_BASE_URL}/{endpoint}",
            timeout=30.0,
            **kwargs
        )
        response.raise_for_status()
        return response.json()
```

## Async/Await Best Practices

Always use async/await for network requests and I/O operations:

```python
# Good: Async network request
async def fetch_data(resource_id: str) -> dict:
    async with httpx.AsyncClient() as client:
        response = await client.get(f"{API_URL}/resource/{resource_id}")
        response.raise_for_status()
        return response.json()

# Bad: Synchronous request
def fetch_data(resource_id: str) -> dict:
    response = requests.get(f"{API_URL}/resource/{resource_id}")  # Blocks
    return response.json()
```

## Type Hints

Use type hints throughout:

```python
from typing import Optional, List, Dict, Any

async def get_user(user_id: str) -> Dict[str, Any]:
    data = await fetch_user(user_id)
    return {"id": data["id"], "name": data["name"]}
```

## Tool Docstrings

Every tool must have comprehensive docstrings with explicit type information:

```python
async def search_users(params: UserSearchInput) -> str:
    '''
    Search for users in the Example system by name, email, or team.

    This tool searches across all user profiles in the Example platform,
    supporting partial matches and various search filters. It does NOT
    create or modify users, only searches existing ones.

    Args:
        params (UserSearchInput): Validated input parameters containing:
            - query (str): Search string to match against names/emails (e.g., "john", "@example.com", "team:marketing")
            - limit (Optional[int]): Maximum results to return, between 1-100 (default: 20)
            - offset (Optional[int]): Number of results to skip for pagination (default: 0)

    Returns:
        str: JSON-formatted string containing search results with the following schema:

        Success response:
        {
            "total": int,           # Total number of matches found
            "count": int,           # Number of results in this response
            "offset": int,          # Current pagination offset
            "users": [
                {
                    "id": str,      # User ID (e.g., "U123456789")
                    "name": str,    # Full name (e.g., "John Doe")
                    "email": str,   # Email address (e.g., "john@example.com")
                    "team": str     # Team name (e.g., "Marketing") - optional
                }
            ]
        }

        Error response:
        "Error: <error message>" or "No users found matching '<query>'"

    Examples:
        - Use when: "Find all marketing team members" -> params with query="team:marketing"
        - Use when: "Search for John's account" -> params with query="john"
        - Don't use when: You need to create a user (use example_create_user instead)
        - Don't use when: You have a user ID and need full details (use example_get_user instead)

    Error Handling:
        - Input validation errors are handled by Pydantic model
        - Returns "Error: Rate limit exceeded" if too many requests (429 status)
        - Returns "Error: Invalid API authentication" if API key is invalid (401 status)
        - Returns formatted list of results or "No users found matching 'query'"
    '''
```

## Complete Example

See below for a complete Python MCP server example:

```python
#!/usr/bin/env python3
'''
MCP Server for Example Service.

This server provides tools to interact with Example API, including user search,
project management, and data export capabilities.
'''

from typing import Optional, List, Dict, Any
from enum import Enum
import httpx
from pydantic import BaseModel, Field, field_validator, ConfigDict
from mcp.server.fastmcp import FastMCP

# Initialize the MCP server
mcp = FastMCP("example_mcp")

# Constants
API_BASE_URL = "https://api.example.com/v1"

# Enums
class ResponseFormat(str, Enum):
    '''Output format for tool responses.'''
    MARKDOWN = "markdown"
    JSON = "json"

# Pydantic Models for Input Validation
class UserSearchInput(BaseModel):
    '''Input model for user search operations.'''
    model_config = ConfigDict(
        str_strip_whitespace=True,
        validate_assignment=True
    )

    query: str = Field(..., description="Search string to match against names/emails", min_length=2, max_length=200)
    limit: Optional[int] = Field(default=20, description="Maximum results to return", ge=1, le=100)
    offset: Optional[int] = Field(default=0, description="Number of results to skip for pagination", ge=0)
    response_format: ResponseFormat = Field(default=ResponseFormat.MARKDOWN, description="Output format")

    @field_validator('query')
    @classmethod
    def validate_query(cls, v: str) -> str:
        if not v.strip():
            raise ValueError("Query cannot be empty or whitespace only")
        return v.strip()

# Shared utility functions
async def _make_api_request(endpoint: str, method: str = "GET", **kwargs) -> dict:
    '''Reusable function for all API calls.'''
    async with httpx.AsyncClient() as client:
        response = await client.request(
            method,
            f"{API_BASE_URL}/{endpoint}",
            timeout=30.0,
            **kwargs
        )
        response.raise_for_status()
        return response.json()

def _handle_api_error(e: Exception) -> str:
    '''Consistent error formatting across all tools.'''
    if isinstance(e, httpx.HTTPStatusError):
        if e.response.status_code == 404:
            return "Error: Resource not found. Please check the ID is correct."
        elif e.response.status_code == 403:
            return "Error: Permission denied. You don't have access to this resource."
        elif e.response.status_code == 429:
            return "Error: Rate limit exceeded. Please wait before making more requests."
        return f"Error: API request failed with status {e.response.status_code}"
    elif isinstance(e, httpx.TimeoutException):
        return "Error: Request timed out. Please try again."
    return f"Error: Unexpected error occurred: {type(e).__name__}"

# Tool definitions
@mcp.tool(
    name="example_search_users",
    annotations={
        "title": "Search Example Users",
        "readOnlyHint": True,
        "destructiveHint": False,
        "idempotentHint": True,
        "openWorldHint": True
    }
)
async def example_search_users(params: UserSearchInput) -> str:
    '''Search for users in the Example system by name, email, or team.

    [Full docstring as shown above]
    '''
    try:
        # Make API request using validated parameters
        data = await _make_api_request(
            "users/search",
            params={
                "q": params.query,
                "limit": params.limit,
                "offset": params.offset
            }
        )

        users = data.get("users", [])
        total = data.get("total", 0)

        if not users:
            return f"No users found matching '{params.query}'"

        # Format response based on requested format
        if params.response_format == ResponseFormat.MARKDOWN:
            lines = [f"# User Search Results: '{params.query}'", ""]
            lines.append(f"Found {total} users (showing {len(users)})")
            lines.append("")

            for user in users:
                lines.append(f"## {user['name']} ({user['id']})")
                lines.append(f"- **Email**: {user['email']}")
                if user.get('team'):
                    lines.append(f"- **Team**: {user['team']}")
                lines.append("")

            return "\n".join(lines)

        else:
            # Machine-readable JSON format
            import json
            response = {
                "total": total,
                "count": len(users),
                "offset": params.offset,
                "users": users
            }
            return json.dumps(response, indent=2)

    except Exception as e:
        return _handle_api_error(e)

if __name__ == "__main__":
    mcp.run()
```

---

## Advanced FastMCP Features

### Context Parameter Injection

FastMCP can automatically inject a `Context` parameter into tools for advanced capabilities like logging, progress reporting, resource reading, and user interaction:

```python
from mcp.server.fastmcp import FastMCP, Context

mcp = FastMCP("example_mcp")

@mcp.tool()
async def advanced_search(query: str, ctx: Context) -> str:
    '''Advanced tool with context access for logging and progress.'''

    # Report progress for long operations
    await ctx.report_progress(0.25, "Starting search...")

    # Log information for debugging
    await ctx.log_info("Processing query", {"query": query, "timestamp": datetime.now()})

    # Perform search
    results = await search_api(query)
    await ctx.report_progress(0.75, "Formatting results...")

    # Access server configuration
    server_name = ctx.fastmcp.name

    return format_results(results)

@mcp.tool()
async def interactive_tool(resource_id: str, ctx: Context) -> str:
    '''Tool that can request additional input from users.'''

    # Request sensitive information when needed
    api_key = await ctx.elicit(
        prompt="Please provide your API key:",
        input_type="password"
    )

    # Use the provided key
    return await api_call(resource_id, api_key)
```

**Context capabilities:**
- `ctx.report_progress(progress, message)` - Report progress for long operations
- `ctx.log_info(message, data)` / `ctx.log_error()` / `ctx.log_debug()` - Logging
- `ctx.elicit(prompt, input_type)` - Request input from users
- `ctx.fastmcp.name` - Access server configuration
- `ctx.read_resource(uri)` - Read MCP resources

### Resource Registration

Expose data as resources for efficient, template-based access:

```python
@mcp.resource("file://documents/{name}")
async def get_document(name: str) -> str:
    '''Expose documents as MCP resources.

    Resources are useful for static or semi-static data that doesn't
    require complex parameters. They use URI templates for flexible access.
    '''
    document_path = f"./docs/{name}"
    with open(document_path, "r") as f:
        return f.read()

@mcp.resource("config://settings/{key}")
async def get_setting(key: str, ctx: Context) -> str:
    '''Expose configuration as resources with context.'''
    settings = await load_settings()
    return json.dumps(settings.get(key, {}))
```

**When to use Resources vs Tools:**
- **Resources**: For data access with simple parameters (URI templates)
- **Tools**: For complex operations with validation and business logic

### Structured Output Types

FastMCP supports multiple return types beyond strings:

```python
from typing import TypedDict
from dataclasses import dataclass
from pydantic import BaseModel

# TypedDict for structured returns
class UserData(TypedDict):
    id: str
    name: str
    email: str

@mcp.tool()
async def get_user_typed(user_id: str) -> UserData:
    '''Returns structured data - FastMCP handles serialization.'''
    return {"id": user_id, "name": "John Doe", "email": "john@example.com"}

# Pydantic models for complex validation
class DetailedUser(BaseModel):
    id: str
    name: str
    email: str
    created_at: datetime
    metadata: Dict[str, Any]

@mcp.tool()
async def get_user_detailed(user_id: str) -> DetailedUser:
    '''Returns Pydantic model - automatically generates schema.'''
    user = await fetch_user(user_id)
    return DetailedUser(**user)
```

### Lifespan Management

Initialize resources that persist across requests:

```python
from contextlib import asynccontextmanager

@asynccontextmanager
async def app_lifespan():
    '''Manage resources that live for the server's lifetime.'''
    # Initialize connections, load config, etc.
    db = await connect_to_database()
    config = load_configuration()

    # Make available to all tools
    yield {"db": db, "config": config}

    # Cleanup on shutdown
    await db.close()

mcp = FastMCP("example_mcp", lifespan=app_lifespan)

@mcp.tool()
async def query_data(query: str, ctx: Context) -> str:
    '''Access lifespan resources through context.'''
    db = ctx.request_context.lifespan_state["db"]
    results = await db.query(query)
    return format_results(results)
```

### Transport Options

FastMCP supports two main transport mechanisms:

```python
# stdio transport (for local tools) - default
if __name__ == "__main__":
    mcp.run()

# Streamable HTTP transport (for remote servers)
if __name__ == "__main__":
    mcp.run(transport="streamable_http", port=8000)
```

**Transport selection:**
- **stdio**: Command-line tools, local integrations, subprocess execution
- **Streamable HTTP**: Web services, remote access, multiple clients

---

## Code Best Practices

### Code Composability and Reusability

Your implementation MUST prioritize composability and code reuse:

1. **Extract Common Functionality**:
   - Create reusable helper functions for operations used across multiple tools
   - Build shared API clients for HTTP requests instead of duplicating code
   - Centralize error handling logic in utility functions
   - Extract business logic into dedicated functions that can be composed
   - Extract shared markdown or JSON field selection & formatting functionality

2. **Avoid Duplication**:
   - NEVER copy-paste similar code between tools
   - If you find yourself writing similar logic twice, extract it into a function
   - Common operations like pagination, filtering, field selection, and formatting should be shared
   - Authentication/authorization logic should be centralized

### Python-Specific Best Practices

1. **Use Type Hints**: Always include type annotations for function parameters and return values
2. **Pydantic Models**: Define clear Pydantic models for all input validation
3. **Avoid Manual Validation**: Let Pydantic handle input validation with constraints
4. **Proper Imports**: Group imports (standard library, third-party, local)
5. **Error Handling**: Use specific exception types (httpx.HTTPStatusError, not generic Exception)
6. **Async Context Managers**: Use `async with` for resources that need cleanup
7. **Constants**: Define module-level constants in UPPER_CASE

## Quality Checklist

Before finalizing your Python MCP server implementation, ensure:

### Strategic Design
- [ ] Tools enable complete workflows, not just API endpoint wrappers
- [ ] Tool names reflect natural task subdivisions
- [ ] Response formats optimize for agent context efficiency
- [ ] Human-readable identifiers used where appropriate
- [ ] Error messages guide agents toward correct usage

### Implementation Quality
- [ ] FOCUSED IMPLEMENTATION: Most important and valuable tools implemented
- [ ] All tools have descriptive names and documentation
- [ ] Return types are consistent across similar operations
- [ ] Error handling is implemented for all external calls
- [ ] Server name follows format: `{service}_mcp`
- [ ] All network operations use async/await
- [ ] Common functionality is extracted into reusable functions
- [ ] Error messages are clear, actionable, and educational
- [ ] Outputs are properly validated and formatted

### Tool Configuration
- [ ] All tools implement 'name' and 'annotations' in the decorator
- [ ] Annotations correctly set (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- [ ] All tools use Pydantic BaseModel for input validation with Field() definitions
- [ ] All Pydantic Fields have explicit types and descriptions with constraints
- [ ] All tools have comprehensive docstrings with explicit input/output types
- [ ] Docstrings include complete schema structure for dict/JSON returns
- [ ] Pydantic models handle input validation (no manual validation needed)

### Advanced Features (where applicable)
- [ ] Context injection used for logging, progress, or elicitation
- [ ] Resources registered for appropriate data endpoints
- [ ] Lifespan management implemented for persistent connections
- [ ] Structured output types used (TypedDict, Pydantic models)
- [ ] Appropriate transport configured (stdio or streamable HTTP)

### Code Quality
- [ ] File includes proper imports including Pydantic imports
- [ ] Pagination is properly implemented where applicable
- [ ] Filtering options are provided for potentially large result sets
- [ ] All async functions are properly defined with `async def`
- [ ] HTTP client usage follows async patterns with proper context managers
- [ ] Type hints are used throughout the code
- [ ] Constants are defined at module level in UPPER_CASE

### Testing
- [ ] Server runs successfully: `python your_server.py --help`
- [ ] All imports resolve correctly
- [ ] Sample tool calls work as expected
- [ ] Error scenarios handled gracefully
FILE:scripts/connections.py
"""Lightweight connection handling for MCP servers."""

from abc import ABC, abstractmethod
from contextlib import AsyncExitStack
from typing import Any

from mcp import ClientSession, StdioServerParameters
from mcp.client.sse import sse_client
from mcp.client.stdio import stdio_client
from mcp.client.streamable_http import streamablehttp_client


class MCPConnection(ABC):
    """Base class for MCP server connections."""

    def __init__(self):
        self.session = None
        self._stack = None

    @abstractmethod
    def _create_context(self):
        """Create the connection context based on connection type."""

    async def __aenter__(self):
        """Initialize MCP server connection."""
        self._stack = AsyncExitStack()
        await self._stack.__aenter__()

        try:
            ctx = self._create_context()
            result = await self._stack.enter_async_context(ctx)

            if len(result) == 2:
                read, write = result
            elif len(result) == 3:
                read, write, _ = result
            else:
                raise ValueError(f"Unexpected context result: {result}")

            session_ctx = ClientSession(read, write)
            self.session = await self._stack.enter_async_context(session_ctx)
            await self.session.initialize()
            return self
        except BaseException:
            await self._stack.__aexit__(None, None, None)
            raise

    async def __aexit__(self, exc_type, exc_val, exc_tb):
        """Clean up MCP server connection resources."""
        if self._stack:
            await self._stack.__aexit__(exc_type, exc_val, exc_tb)
        self.session = None
        self._stack = None

    async def list_tools(self) -> list[dict[str, Any]]:
        """Retrieve available tools from the MCP server."""
        response = await self.session.list_tools()
        return [
            {
                "name": tool.name,
                "description": tool.description,
                "input_schema": tool.inputSchema,
            }
            for tool in response.tools
        ]

    async def call_tool(self, tool_name: str, arguments: dict[str, Any]) -> Any:
        """Call a tool on the MCP server with provided arguments."""
        result = await self.session.call_tool(tool_name, arguments=arguments)
        return result.content


class MCPConnectionStdio(MCPConnection):
    """MCP connection using standard input/output."""

    def __init__(self, command: str, args: list[str] = None, env: dict[str, str] = None):
        super().__init__()
        self.command = command
        self.args = args or []
        self.env = env

    def _create_context(self):
        return stdio_client(
            StdioServerParameters(command=self.command, args=self.args, env=self.env)
        )


class MCPConnectionSSE(MCPConnection):
    """MCP connection using Server-Sent Events."""

    def __init__(self, url: str, headers: dict[str, str] = None):
        super().__init__()
        self.url = url
        self.headers = headers or {}

    def _create_context(self):
        return sse_client(url=self.url, headers=self.headers)


class MCPConnectionHTTP(MCPConnection):
    """MCP connection using Streamable HTTP."""

    def __init__(self, url: str, headers: dict[str, str] = None):
        super().__init__()
        self.url = url
        self.headers = headers or {}

    def _create_context(self):
        return streamablehttp_client(url=self.url, headers=self.headers)


def create_connection(
    transport: str,
    command: str = None,
    args: list[str] = None,
    env: dict[str, str] = None,
    url: str = None,
    headers: dict[str, str] = None,
) -> MCPConnection:
    """Factory function to create the appropriate MCP connection.

    Args:
        transport: Connection type ("stdio", "sse", or "http")
        command: Command to run (stdio only)
        args: Command arguments (stdio only)
        env: Environment variables (stdio only)
        url: Server URL (sse and http only)
        headers: HTTP headers (sse and http only)

    Returns:
        MCPConnection instance
    """
    transport = transport.lower()

    if transport == "stdio":
        if not command:
            raise ValueError("Command is required for stdio transport")
        return MCPConnectionStdio(command=command, args=args, env=env)

    elif transport == "sse":
        if not url:
            raise ValueError("URL is required for sse transport")
        return MCPConnectionSSE(url=url, headers=headers)

    elif transport in ["http", "streamable_http", "streamable-http"]:
        if not url:
            raise ValueError("URL is required for http transport")
        return MCPConnectionHTTP(url=url, headers=headers)

    else:
        raise ValueError(f"Unsupported transport type: {transport}. Use 'stdio', 'sse', or 'http'")
FILE:scripts/evaluation.py
"""MCP Server Evaluation Harness

This script evaluates MCP servers by running test questions against them using Claude.
"""

import argparse
import asyncio
import json
import re
import sys
import time
import traceback
import xml.etree.ElementTree as ET
from pathlib import Path
from typing import Any

from anthropic import Anthropic

from connections import create_connection

EVALUATION_PROMPT = """You are an AI assistant with access to tools.

When given a task, you MUST:
1. Use the available tools to complete the task
2. Provide summary of each step in your approach, wrapped in <summary> tags
3. Provide feedback on the tools provided, wrapped in <feedback> tags
4. Provide your final response, wrapped in <response> tags

Summary Requirements:
- In your <summary> tags, you must explain:
  - The steps you took to complete the task
  - Which tools you used, in what order, and why
  - The inputs you provided to each tool
  - The outputs you received from each tool
  - A summary for how you arrived at the response

Feedback Requirements:
- In your <feedback> tags, provide constructive feedback on the tools:
  - Comment on tool names: Are they clear and descriptive?
  - Comment on input parameters: Are they well-documented? Are required vs optional parameters clear?
  - Comment on descriptions: Do they accurately describe what the tool does?
  - Comment on any errors encountered during tool usage: Did the tool fail to execute? Did the tool return too many tokens?
  - Identify specific areas for improvement and explain WHY they would help
  - Be specific and actionable in your suggestions

Response Requirements:
- Your response should be concise and directly address what was asked
- Always wrap your final response in <response> tags
- If you cannot solve the task return <response>NOT_FOUND</response>
- For numeric responses, provide just the number
- For IDs, provide just the ID
- For names or text, provide the exact text requested
- Your response should go last"""


def parse_evaluation_file(file_path: Path) -> list[dict[str, Any]]:
    """Parse XML evaluation file with qa_pair elements."""
    try:
        tree = ET.parse(file_path)
        root = tree.getroot()
        evaluations = []

        for qa_pair in root.findall(".//qa_pair"):
            question_elem = qa_pair.find("question")
            answer_elem = qa_pair.find("answer")

            if question_elem is not None and answer_elem is not None:
                evaluations.append({
                    "question": (question_elem.text or "").strip(),
                    "answer": (answer_elem.text or "").strip(),
                })

        return evaluations
    except Exception as e:
        print(f"Error parsing evaluation file {file_path}: {e}")
        return []


def extract_xml_content(text: str, tag: str) -> str | None:
    """Extract content from XML tags."""
    pattern = rf"<{tag}>(.*?)</{tag}>"
    matches = re.findall(pattern, text, re.DOTALL)
    return matches[-1].strip() if matches else None


async def agent_loop(
    client: Anthropic,
    model: str,
    question: str,
    tools: list[dict[str, Any]],
    connection: Any,
) -> tuple[str, dict[str, Any]]:
    """Run the agent loop with MCP tools."""
    messages = [{"role": "user", "content": question}]

    response = await asyncio.to_thread(
        client.messages.create,
        model=model,
        max_tokens=4096,
        system=EVALUATION_PROMPT,
        messages=messages,
        tools=tools,
    )

    messages.append({"role": "assistant", "content": response.content})

    tool_metrics = {}

    while response.stop_reason == "tool_use":
        tool_use = next(block for block in response.content if block.type == "tool_use")
        tool_name = tool_use.name
        tool_input = tool_use.input

        tool_start_ts = time.time()
        try:
            tool_result = await connection.call_tool(tool_name, tool_input)
            tool_response = json.dumps(tool_result) if isinstance(tool_result, (dict, list)) else str(tool_result)
        except Exception as e:
            tool_response = f"Error executing tool {tool_name}: {str(e)}\n"
            tool_response += traceback.format_exc()
        tool_duration = time.time() - tool_start_ts

        if tool_name not in tool_metrics:
            tool_metrics[tool_name] = {"count": 0, "durations": []}
        tool_metrics[tool_name]["count"] += 1
        tool_metrics[tool_name]["durations"].append(tool_duration)

        messages.append({
            "role": "user",
            "content": [{
                "type": "tool_result",
                "tool_use_id": tool_use.id,
                "content": tool_response,
            }]
        })

        response = await asyncio.to_thread(
            client.messages.create,
            model=model,
            max_tokens=4096,
            system=EVALUATION_PROMPT,
            messages=messages,
            tools=tools,
        )
        messages.append({"role": "assistant", "content": response.content})

    response_text = next(
        (block.text for block in response.content if hasattr(block, "text")),
        None,
    )
    return response_text, tool_metrics


async def evaluate_single_task(
    client: Anthropic,
    model: str,
    qa_pair: dict[str, Any],
    tools: list[dict[str, Any]],
    connection: Any,
    task_index: int,
) -> dict[str, Any]:
    """Evaluate a single QA pair with the given tools."""
    start_time = time.time()

    print(f"Task {task_index + 1}: Running task with question: {qa_pair['question']}")
    response, tool_metrics = await agent_loop(client, model, qa_pair["question"], tools, connection)

    response_value = extract_xml_content(response, "response")
    summary = extract_xml_content(response, "summary")
    feedback = extract_xml_content(response, "feedback")

    duration_seconds = time.time() - start_time

    return {
        "question": qa_pair["question"],
        "expected": qa_pair["answer"],
        "actual": response_value,
        "score": int(response_value == qa_pair["answer"]) if response_value else 0,
        "total_duration": duration_seconds,
        "tool_calls": tool_metrics,
        "num_tool_calls": sum(len(metrics["durations"]) for metrics in tool_metrics.values()),
        "summary": summary,
        "feedback": feedback,
    }


REPORT_HEADER = """
# Evaluation Report

## Summary

- **Accuracy**: {correct}/{total} ({accuracy:.1f}%)
- **Average Task Duration**: {average_duration_s:.2f}s
- **Average Tool Calls per Task**: {average_tool_calls:.2f}
- **Total Tool Calls**: {total_tool_calls}

---
"""

TASK_TEMPLATE = """
### Task {task_num}

**Question**: {question}
**Ground Truth Answer**: `{expected_answer}`
**Actual Answer**: `{actual_answer}`
**Correct**: {correct_indicator}
**Duration**: {total_duration:.2f}s
**Tool Calls**: {tool_calls}

**Summary**
{summary}

**Feedback**
{feedback}

---
"""


async def run_evaluation(
    eval_path: Path,
    connection: Any,
    model: str = "claude-3-7-sonnet-20250219",
) -> str:
    """Run evaluation with MCP server tools."""
    print("🚀 Starting Evaluation")

    client = Anthropic()

    tools = await connection.list_tools()
    print(f"📋 Loaded {len(tools)} tools from MCP server")

    qa_pairs = parse_evaluation_file(eval_path)
    print(f"📋 Loaded {len(qa_pairs)} evaluation tasks")

    results = []
    for i, qa_pair in enumerate(qa_pairs):
        print(f"Processing task {i + 1}/{len(qa_pairs)}")
        result = await evaluate_single_task(client, model, qa_pair, tools, connection, i)
        results.append(result)

    correct = sum(r["score"] for r in results)
    accuracy = (correct / len(results)) * 100 if results else 0
    average_duration_s = sum(r["total_duration"] for r in results) / len(results) if results else 0
    average_tool_calls = sum(r["num_tool_calls"] for r in results) / len(results) if results else 0
    total_tool_calls = sum(r["num_tool_calls"] for r in results)

    report = REPORT_HEADER.format(
        correct=correct,
        total=len(results),
        accuracy=accuracy,
        average_duration_s=average_duration_s,
        average_tool_calls=average_tool_calls,
        total_tool_calls=total_tool_calls,
    )

    report += "".join([
        TASK_TEMPLATE.format(
            task_num=i + 1,
            question=qa_pair["question"],
            expected_answer=qa_pair["answer"],
            actual_answer=result["actual"] or "N/A",
            correct_indicator="✅" if result["score"] else "❌",
            total_duration=result["total_duration"],
            tool_calls=json.dumps(result["tool_calls"], indent=2),
            summary=result["summary"] or "N/A",
            feedback=result["feedback"] or "N/A",
        )
        for i, (qa_pair, result) in enumerate(zip(qa_pairs, results))
    ])

    return report


def parse_headers(header_list: list[str]) -> dict[str, str]:
    """Parse header strings in format 'Key: Value' into a dictionary."""
    headers = {}
    if not header_list:
        return headers

    for header in header_list:
        if ":" in header:
            key, value = header.split(":", 1)
            headers[key.strip()] = value.strip()
        else:
            print(f"Warning: Ignoring malformed header: {header}")
    return headers


def parse_env_vars(env_list: list[str]) -> dict[str, str]:
    """Parse environment variable strings in format 'KEY=VALUE' into a dictionary."""
    env = {}
    if not env_list:
        return env

    for env_var in env_list:
        if "=" in env_var:
            key, value = env_var.split("=", 1)
            env[key.strip()] = value.strip()
        else:
            print(f"Warning: Ignoring malformed environment variable: {env_var}")
    return env


async def main():
    parser = argparse.ArgumentParser(
        description="Evaluate MCP servers using test questions",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
Examples:
  # Evaluate a local stdio MCP server
  python evaluation.py -t stdio -c python -a my_server.py eval.xml

  # Evaluate an SSE MCP server
  python evaluation.py -t sse -u https://example.com/mcp -H "Authorization: Bearer token" eval.xml

  # Evaluate an HTTP MCP server with custom model
  python evaluation.py -t http -u https://example.com/mcp -m claude-3-5-sonnet-20241022 eval.xml
        """,
    )

    parser.add_argument("eval_file", type=Path, help="Path to evaluation XML file")
    parser.add_argument("-t", "--transport", choices=["stdio", "sse", "http"], default="stdio", help="Transport type (default: stdio)")
    parser.add_argument("-m", "--model", default="claude-3-7-sonnet-20250219", help="Claude model to use (default: claude-3-7-sonnet-20250219)")

    stdio_group = parser.add_argument_group("stdio options")
    stdio_group.add_argument("-c", "--command", help="Command to run MCP server (stdio only)")
    stdio_group.add_argument("-a", "--args", nargs="+", help="Arguments for the command (stdio only)")
    stdio_group.add_argument("-e", "--env", nargs="+", help="Environment variables in KEY=VALUE format (stdio only)")

    remote_group = parser.add_argument_group("sse/http options")
    remote_group.add_argument("-u", "--url", help="MCP server URL (sse/http only)")
    remote_group.add_argument("-H", "--header", nargs="+", dest="headers", help="HTTP headers in 'Key: Value' format (sse/http only)")

    parser.add_argument("-o", "--output", type=Path, help="Output file for evaluation report (default: stdout)")

    args = parser.parse_args()

    if not args.eval_file.exists():
        print(f"Error: Evaluation file not found: {args.eval_file}")
        sys.exit(1)

    headers = parse_headers(args.headers) if args.headers else None
    env_vars = parse_env_vars(args.env) if args.env else None

    try:
        connection = create_connection(
            transport=args.transport,
            command=args.command,
            args=args.args,
            env=env_vars,
            url=args.url,
            headers=headers,
        )
    except ValueError as e:
        print(f"Error: {e}")
        sys.exit(1)

    print(f"🔗 Connecting to MCP server via {args.transport}...")

    async with connection:
        print("✅ Connected successfully")
        report = await run_evaluation(args.eval_file, connection, args.model)

        if args.output:
            args.output.write_text(report)
            print(f"\n✅ Report saved to {args.output}")
        else:
            print("\n" + report)


if __name__ == "__main__":
    asyncio.run(main())
FILE:scripts/example_evaluation.xml
<evaluation>
   <qa_pair>
      <question>Calculate the compound interest on $10,000 invested at 5% annual interest rate, compounded monthly for 3 years. What is the final amount in dollars (rounded to 2 decimal places)?</question>
      <answer>11614.72</answer>
   </qa_pair>
   <qa_pair>
      <question>A projectile is launched at a 45-degree angle with an initial velocity of 50 m/s. Calculate the total distance (in meters) it has traveled from the launch point after 2 seconds, assuming g=9.8 m/s². Round to 2 decimal places.</question>
      <answer>87.25</answer>
   </qa_pair>
   <qa_pair>
      <question>A sphere has a volume of 500 cubic meters. Calculate its surface area in square meters. Round to 2 decimal places.</question>
      <answer>304.65</answer>
   </qa_pair>
   <qa_pair>
      <question>Calculate the population standard deviation of this dataset: [12, 15, 18, 22, 25, 30, 35]. Round to 2 decimal places.</question>
      <answer>7.61</answer>
   </qa_pair>
   <qa_pair>
      <question>Calculate the pH of a solution with a hydrogen ion concentration of 3.5 × 10^-5 M. Round to 2 decimal places.</question>
      <answer>4.46</answer>
   </qa_pair>
</evaluation>
FILE:scripts/requirements.txt
anthropic>=0.39.0
mcp>=1.1.0

---
name: prompt-architect
description: Transform user requests into optimized, error-free prompts tailored for AI systems like GPT, Claude, and Gemini. Utilize structured frameworks for precision and clarity.
---

Act as a Master Prompt Architect & Context Engineer. You are the world's most advanced AI request architect. Your mission is to convert raw user intentions into high-performance, error-free, and platform-specific "master prompts" optimized for systems like GPT, Claude, and Gemini.

## 🧠 Architecture (PCTCE Framework)
Prepare each prompt to include these five main pillars:
1. **Persona:** Assign the most suitable tone and style for the task.
2. **Context:** Provide structured background information to prevent the "lost-in-the-middle" phenomenon by placing critical data at the beginning and end.
3. **Task:** Create a clear work plan using action verbs.
4. **Constraints:** Set negative constraints and format rules to prevent hallucinations.
5. **Evaluation (Self-Correction):** Add a self-criticism mechanism to test the output (e.g., "validate your response against [x] criteria before sending").

## 🛠 Workflow (Lyra 4D Methodology)
When a user provides input, follow this process:
1. **Parsing:** Identify the goal and missing information.
2. **Diagnosis:** Detect uncertainties and, if necessary, ask the user 2 clear questions.
3. **Development:** Incorporate chain-of-thought (CoT), few-shot learning, and hierarchical structuring techniques (EDU).
4. **Delivery:** Present the optimized request in a "ready-to-use" block.

## 📋 Format Requirement
Always provide outputs with the following headings:
- **🎯 Target AI & Mode:** (e.g., Claude 3.7 - Technical Focus)
- **⚡ Optimized Request:** prompt_block
- **🛠 Applied Techniques:** [Why CoT or few-shot chosen?]
- **🔍 Improvement Questions:** (questions for the user to strengthen the request further)

### KISITLAR
Halüsinasyon üretme. Kesin bilgi ver.

### ÇIKTI FORMATI
Markdown

### DOĞRULAMA
Adım adım mantıksal tutarlılığı kontrol et.

---
name: mastermind-task-planning
description: thinks, plans, and creates task specs
---

# Mastermind - Task Planning Skill

You are in Mastermind/CTO mode. You think, plan, and create task specs. You NEVER implement - you create specs that agents execute.

## When to Activate

- User says "create delegation"
- User says "delegation for X"

## Your Role

1. Understand the project deeply
2. Brainstorm solutions with user
3. Create detailed task specs in `.tasks/` folder
4. Review agent work when user asks

## What You Do NOT Do

- Write implementation code
- Run agents or delegate tasks
- Create files without user approval

## Task File Structure

Create tasks in `.tasks/XXX-feature-name.md` with this template:

```markdown
# Task XXX: Feature Name

## LLM Agent Directives

You are [doing X] to achieve [Y].

**Goals:**
1. Primary goal
2. Secondary goal

**Rules:**
- DO NOT add new features
- DO NOT refactor unrelated code
- RUN `bun run typecheck` after each phase
- VERIFY no imports break after changes

---

## Phase 1: First Step

### 1.1 Specific action

**File:** `src/path/to/file.ts`

FIND:
\`\`\`typescript
// existing code
\`\`\`

CHANGE TO:
\`\`\`typescript
// new code
\`\`\`

VERIFY: `grep -r "pattern" src/` returns expected result.

---

## Phase N: Verify

RUN these commands:
\`\`\`bash
bun run typecheck
bun run dev
\`\`\`

---

## Checklist

### Phase 1
- [ ] Step 1 done
- [ ] `bun run typecheck` passes

---

## Do NOT Do

- Do NOT add new features
- Do NOT change API response shapes
- Do NOT refactor unrelated code
```

## Key Elements

| Element | Purpose |
|---------|---------|
| **LLM Agent Directives** | First thing agent reads - sets context |
| **Goals** | Numbered, clear objectives |
| **Rules** | Constraints to prevent scope creep |
| **Phases** | Break work into verifiable chunks |
| **FIND/CHANGE TO** | Exact code transformations |
| **VERIFY** | Commands to confirm each step |
| **Checklist** | Agent marks `[ ]` → `[x]` as it works |
| **Do NOT Do** | Explicit anti-patterns to avoid |

## Workflow

```
User Request
    ↓
Discuss & brainstorm with user
    ↓
Draft task spec, show to user
    ↓
User approves → Create task file
    ↓
User delegates to agent
    ↓
Agent completes → User tells you
    ↓
Review agent's work
    ↓
Pass → Mark complete | Fail → Retry
```

## Task Numbering

- Check existing tasks in `.tasks/` folder
- Use next sequential number: 001, 002, 003...
- Format: `XXX-kebab-case-name.md`

## First Time Setup

If `.tasks/` folder doesn't exist, create it and optionally create `CONTEXT.md` with project info.

---
name: seo-fundamentals
description: SEO fundamentals, E-E-A-T, Core Web Vitals, and 2025 Google algorithm updates
version: 1.0
priority: high
tags: [seo, marketing, google, e-e-a-t, core-web-vitals]
---

# SEO Fundamentals (2025)

## Core Framework: E-E-A-T

```
Experience     → First-hand experience, real stories
Expertise      → Credentials, certifications, knowledge
Authoritativeness → Backlinks, media mentions, recognition
Trustworthiness  → HTTPS, contact info, transparency, reviews
```

## 2025 Algorithm Updates

| Update | Impact | Focus |
|--------|--------|-------|
| March 2025 Core | 63% SERP fluctuation | Content quality |
| June 2025 Core | E-E-A-T emphasis | Authority signals |
| Helpful Content | AI content penalties | People-first content |

## Core Web Vitals Targets

| Metric | Target | Measurement |
|--------|--------|-------------|
| **LCP** | < 2.5s | Largest Contentful Paint |
| **INP** | < 200ms | Interaction to Next Paint |
| **CLS** | < 0.1 | Cumulative Layout Shift |

## Technical SEO Checklist

```
Site Structure:
☐ XML sitemap submitted
☐ robots.txt configured
☐ Canonical tags correct
☐ Hreflang tags (multilingual)
☐ 301 redirects proper
☐ No 404 errors

Performance:
☐ Images optimized (WebP)
☐ Lazy loading
☐ Minification (CSS/JS/HTML)
☐ GZIP/Brotli compression
☐ Browser caching
☐ CDN active

Mobile:
☐ Responsive design
☐ Mobile-friendly test passed
☐ Touch targets 48x48px min
☐ Font size 16px min
☐ Viewport meta correct

Structured Data:
☐ Article schema
☐ Organization schema
☐ Person/Author schema
☐ FAQPage schema
☐ Breadcrumb schema
☐ Review/Rating schema
```

## AI Content Guidelines

```
❌ Don't:
- Publish purely AI-generated content
- Skip fact-checking
- Create duplicate content
- Keyword stuffing

✅ Do:
- AI draft + human edit
- Add original insights
- Expert review
- E-E-A-T principles
- Plagiarism check
```

## Content Format for SEO Success

```
Title: Question-based or keyword-rich
├── Meta description (150-160 chars)
├── H1: Main keyword
├── H2: Related topics
│   ├── H3: Subtopics
│   └── Bullet points/lists
├── FAQ section (with FAQPage schema)
├── Internal links to related content
└── External links to authoritative sources

Elements:
☐ Author bio with credentials
☐ "Last updated" date
☐ Original statistics/data
☐ Citations and references
☐ Summary/TL;DR box
☐ Visual content (images, charts)
☐ Social share buttons
```

## Quick Reference

```javascript
// Essential meta tags
<meta name="description" content="...">
<meta name="viewport" content="width=device-width, initial-scale=1">
<link rel="canonical" href="https://example.com/page">

// Open Graph for social
<meta property="og:title" content="...">
<meta property="og:description" content="...">
<meta property="og:image" content="...">

// Schema markup example
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Article",
  "headline": "...",
  "author": { "@type": "Person", "name": "..." },
  "datePublished": "2025-12-30",
  "dateModified": "2025-12-30"
}
</script>
```

## SEO Tools (2025)

| Tool | Purpose |
|------|---------|
| Google Search Console | Performance, indexing |
| PageSpeed Insights | Core Web Vitals |
| Lighthouse | Technical audit |
| Semrush/Ahrefs | Keywords, backlinks |
| Surfer SEO | Content optimization |

---

**Last Updated:** 2025-12-30

---
name: comprehensive-pos-application-development-with-fifo-and-reporting
description: Develop a full-featured Point of Sales (POS) application integrating inventory management, FIFO costing, and daily sales reporting.
---

# Comprehensive POS Application Development with FIFO and Reporting

Act as a Software Developer. You are tasked with creating a comprehensive Point of Sales (POS) application with integrated daily sales reporting functionality.

Your task is to develop:
- **Core POS Features:**
  - Product inventory management with buy price and sell price tracking
  - Sales transaction processing
  - Real-time inventory updates
  - User-friendly interface for cashiers

- **FIFO Implementation:**
  - Implement First-In-First-Out inventory management
  - Track product batches with purchase dates
  - Automatically sell oldest stock first
  - Maintain accurate cost calculations based on FIFO methodology

- **Daily Sales Report Features:**
  - Generate comprehensive daily sales reports including:
    - Total daily sales revenue
    - Total daily profit (calculated as: sell price - buy price using FIFO costing)
    - Number of transactions
    - Best-selling products
    - Inventory levels after sales

**Technical Specifications:**
- Use a modern programming language (next js)
- Include a database design for storing products, transactions, and inventory batches
- Implement proper error handling and data validation
- Create a clean, intuitive user interface
- Include sample data for demonstration

**Deliverables:**
1. Complete source code with comments
2. Database schema/structure
3. Installation and setup instructions
4. Sample screenshots or demo of key features
5. Brief documentation explaining the FIFO implementation

Ensure the application is production-ready with proper data persistence and can handle multiple daily transactions efficiently.

---
name: codebase-wiki-documentation-skill
description: A skill for generating comprehensive WIKI.md documentation for codebases using the Language Server Protocol for precise analysis, ideal for documenting code structure and dependencies.
---

# Codebase WIKI Documentation Skill

Act as a Codebase Documentation Specialist. You are an expert in generating detailed WIKI.md documentation for various codebases using Language Server Protocol (LSP) for precise code analysis.

Your task is to:
- Analyze the provided codebase using LSP.
- Generate a comprehensive WIKI.md document.
- Include architectural diagrams, API references, and data flow documentation.

You will:
- Detect language from configuration files like `package.json`, `pyproject.toml`, `go.mod`, etc.
- Start the appropriate LSP server for the detected language.
- Query the LSP for symbols, references, types, and call hierarchy.
- If LSP unavailable, scripts fall back to AST/regex analysis.
- Use Mermaid diagrams extensively (flowchart, sequenceDiagram, classDiagram, erDiagram).

Required Sections:
1. Project Overview (tech stack, dependencies)
2. Architecture (Mermaid flowchart)
3. Project Structure (directory tree)
4. Core Components (classes, functions, APIs)
5. Data Flow (Mermaid sequenceDiagram)
6. Data Model (Mermaid erDiagram, classDiagram)
7. API Reference
8. Configuration
9. Getting Started
10. Development Guide

Rules:
- Support TypeScript, JavaScript, Python, Go, Rust, Java, C/C++, Julia ... projects.
- Exclude directories such as `node_modules/`, `venv/`, `.git/`, `dist/`, `build/`.
- Focus on `src/` or `lib/` for large codebases and prioritize entry points like `main.py`, `index.ts`, `App.tsx`. 

---
name: comprehensive-web-application-development-with-security-and-performance-optimization
description: Guide to building a full-stack web application with secure user authentication, high performance, and robust user interaction features.
---

# Comprehensive Web Application Development with Security and Performance Optimization

Act as a Full-Stack Web Developer. You are responsible for building a secure and high-performance web application.

Your task includes:
- Implementing secure user registration and login systems.
- Ensuring real-time commenting, feedback, and likes functionalities.
- Optimizing the website for speed and performance.
- Encrypting sensitive data to prevent unauthorized access.
- Implementing measures to prevent users from easily inspecting or reverse-engineering the website's code.

You will:
- Use modern web technologies to build the front-end and back-end.
- Implement encryption techniques for sensitive data.
- Optimize server responses for faster load times.
- Ensure user interactions are seamless and efficient.

Rules:
- All data storage must be secure and encrypted.
- Authentication systems must be robust and protected against common vulnerabilities.
- The website must be responsive and user-friendly.

Variables:
- framework - The web development framework to use (e.g., React, Angular, Vue).
- backendTech - Backend technology (e.g., Node.js, Django, Ruby on Rails).
- database - Database system (e.g., MySQL, MongoDB).
- encryptionMethod - Encryption method for sensitive data.

---
name: website-creation-command
description: A skill to guide users in creating a website similar to a specified one, offering step-by-step instructions and best practices.
---

# Website Creation Command

Act as a Website Development Consultant. You are an expert in designing and developing websites with a focus on creating user-friendly and visually appealing interfaces.

Your task is to assist users in creating a website similar to the one specified.

You will:
- Analyze the specified website to identify key features and design elements
- Provide a step-by-step guide on recreating these features
- Suggest best practices for web development including responsive design and accessibility
- Recommend tools and technologies suitable for the project

Rules:
- Ensure the design is responsive and works on all devices
- Maintain high standards of accessibility and usability

Variables:
- websiteURL - URL of the website to be analyzed
- WordPress - Preferred platform for development
- modern - Design style preference

---
name: agent-organization-expert
description: Multi-agent orchestration skill for team assembly, task decomposition, workflow optimization, and coordination strategies to achieve optimal team performance and resource utilization.
---

# Agent Organization

Assemble and coordinate multi-agent teams through systematic task analysis, capability mapping, and workflow design.

## Configuration

- **Agent Count**: 3
- **Task Type**: general
- **Orchestration Pattern**: parallel
- **Max Concurrency**: 5
- **Timeout (seconds)**: 300
- **Retry Count**: 3

## Core Process

1. **Analyze Requirements**: Understand task scope, constraints, and success criteria
2. **Map Capabilities**: Match available agents to required skills
3. **Design Workflow**: Create execution plan with dependencies and checkpoints
4. **Orchestrate Execution**: Coordinate 3 agents and monitor progress
5. **Optimize Continuously**: Adapt based on performance feedback

## Task Decomposition

### Requirement Analysis
- Break complex tasks into discrete subtasks
- Identify input/output requirements for each subtask
- Estimate complexity and resource needs per component
- Define clear success criteria for each unit

### Dependency Mapping
- Document task execution order constraints
- Identify data dependencies between subtasks
- Map resource sharing requirements
- Detect potential bottlenecks and conflicts

### Timeline Planning
- Sequence tasks respecting dependencies
- Identify parallelization opportunities (up to 5 concurrent)
- Allocate buffer time for high-risk components
- Define checkpoints for progress validation

## Agent Selection

### Capability Matching
Select agents based on:
- Required skills versus agent specializations
- Historical performance on similar tasks
- Current availability and workload capacity
- Cost efficiency for the task complexity

### Selection Criteria Priority
1. **Capability fit**: Agent must possess required skills
2. **Track record**: Prefer agents with proven success
3. **Availability**: Sufficient capacity for timely completion
4. **Cost**: Optimize resource utilization within constraints

### Backup Planning
- Identify alternate agents for critical roles
- Define failover triggers and handoff procedures
- Maintain redundancy for single-point-of-failure tasks

## Team Assembly

### Composition Principles
- Ensure complete skill coverage for all subtasks
- Balance workload across 3 team members
- Minimize communication overhead
- Include redundancy for critical functions

### Role Assignment
- Match agents to subtasks based on strength
- Define clear ownership and accountability
- Establish communication channels between dependent roles
- Document escalation paths for blockers

### Team Sizing
- Smaller teams for tightly coupled tasks
- Larger teams for parallelizable workloads
- Consider coordination overhead in sizing decisions
- Scale dynamically based on progress

## Orchestration Patterns

### Sequential Execution
Use when tasks have strict ordering requirements:
- Task B requires output from Task A
- State must be consistent between steps
- Error handling requires ordered rollback

### Parallel Processing
Use when tasks are independent (parallel):
- No data dependencies between tasks
- Separate resource requirements
- Results can be aggregated after completion
- Maximum 5 concurrent operations

### Pipeline Pattern
Use for streaming or continuous processing:
- Each stage processes and forwards results
- Enables concurrent execution of different stages
- Reduces overall latency for multi-step workflows

### Hierarchical Delegation
Use for complex tasks requiring sub-orchestration:
- Lead agent coordinates sub-teams
- Each sub-team handles a domain
- Results aggregate upward through hierarchy

### Map-Reduce
Use for large-scale data processing:
- Map phase distributes work across agents
- Each agent processes a partition
- Reduce phase combines results

## Workflow Design

### Process Structure
1. **Entry point**: Validate inputs and initialize state
2. **Execution phases**: Ordered task groupings
3. **Checkpoints**: State persistence and validation points
4. **Exit point**: Result aggregation and cleanup

### Control Flow
- Define branching conditions for alternative paths
- Specify retry policies for transient failures (max 3 retries)
- Establish timeout thresholds per phase (300s default)
- Plan graceful degradation for partial failures

### Data Flow
- Document data transformations between stages
- Specify data formats and validation rules
- Plan for data persistence at checkpoints
- Handle data cleanup after completion

## Coordination Strategies

### Communication Patterns
- **Direct**: Agent-to-agent for tight coupling
- **Broadcast**: One-to-many for status updates
- **Queue-based**: Asynchronous for decoupled tasks
- **Event-driven**: Reactive to state changes

### Synchronization
- Define sync points for dependent tasks
- Implement waiting mechanisms with timeouts (300s)
- Handle out-of-order completion gracefully
- Maintain consistent state across agents

### Conflict Resolution
- Establish priority rules for resource contention
- Define arbitration mechanisms for conflicts
- Document rollback procedures for deadlocks
- Prevent conflicts through careful scheduling

## Performance Optimization

### Load Balancing
- Distribute work based on agent capacity
- Monitor utilization and rebalance dynamically
- Avoid overloading high-performing agents
- Consider agent locality for data-intensive tasks

### Bottleneck Management
- Identify slow stages through monitoring
- Add capacity to constrained resources
- Restructure workflows to reduce dependencies
- Cache intermediate results where beneficial

### Resource Efficiency
- Pool shared resources across agents
- Release resources promptly after use
- Batch similar operations to reduce overhead
- Monitor and alert on resource waste

## Monitoring and Adaptation

### Progress Tracking
- Monitor completion status per task
- Track time spent versus estimates
- Identify tasks at risk of delay
- Report aggregated progress to stakeholders

### Performance Metrics
- Task completion rate and latency
- Agent utilization and throughput
- Error rates and recovery times
- Resource consumption and cost

### Dynamic Adjustment
- Reallocate agents based on progress
- Adjust priorities based on blockers
- Scale team size based on workload
- Modify workflow based on learning

## Error Handling

### Failure Detection
- Monitor for task failures and timeouts (300s threshold)
- Detect agent unavailability promptly
- Identify cascade failure patterns
- Alert on anomalous behavior

### Recovery Procedures
- Retry transient failures with backoff (up to 3 attempts)
- Failover to backup agents when needed
- Rollback to last checkpoint on critical failure
- Escalate unrecoverable issues

### Prevention
- Validate inputs before execution
- Test agent availability before assignment
- Design for graceful degradation
- Build redundancy into critical paths

## Quality Assurance

### Validation Gates
- Verify outputs at each checkpoint
- Cross-check results from parallel tasks
- Validate final aggregated results
- Confirm success criteria are met

### Performance Standards
- Agent selection accuracy target: >95%
- Task completion rate target: >99%
- Response time target: <5 seconds
- Resource utilization: optimal range 60-80%

## Best Practices

### Planning
- Invest time in thorough task analysis
- Document assumptions and constraints
- Plan for failure scenarios upfront
- Define clear success metrics

### Execution
- Start with minimal viable team (3 agents)
- Scale based on observed needs
- Maintain clear communication channels
- Track progress against milestones

### Learning
- Capture performance data for analysis
- Identify patterns in successes and failures
- Refine selection and coordination strategies
- Share learnings across future orchestrations

---
name: accessibility-testing-superpower
description: |
  Performs WCAG compliance audits and accessibility remediation for web applications.
  Use when: 1) Auditing UI for WCAG 2.1/2.2 compliance 2) Fixing screen reader or keyboard navigation issues 3) Implementing ARIA patterns correctly 4) Reviewing color contrast and visual accessibility 5) Creating accessible forms or interactive components
---

# Accessibility Testing Workflow

## Configuration

- **WCAG Level**: AA
- **Component Under Test**: Page
- **Compliance Standard**: WCAG 2.1
- **Minimum Lighthouse Score**: 90
- **Primary Screen Reader**: NVDA
- **Test Framework**: jest-axe

## Audit Decision Tree

```
Accessibility request received
|
+-- New component/page?
|   +-- Run automated scan first (axe-core, Lighthouse)
|   +-- Keyboard navigation test
|   +-- Screen reader announcement check
|   +-- Color contrast verification
|
+-- Existing violation to fix?
|   +-- Identify WCAG success criterion
|   +-- Check if semantic HTML solves it
|   +-- Apply ARIA only when HTML insufficient
|   +-- Verify fix with assistive technology
|
+-- Compliance audit?
    +-- Automated scan (catches ~30% of issues)
    +-- Manual testing checklist
    +-- Document violations by severity
    +-- Create remediation roadmap
```

## WCAG Quick Reference

### Severity Classification

| Severity | Impact | Examples | Fix Timeline |
|----------|--------|----------|--------------|
| Critical | Blocks access entirely | No keyboard focus, empty buttons, missing alt on functional images | Immediate |
| Serious | Major barriers | Poor contrast, missing form labels, no skip links | Within sprint |
| Moderate | Difficult but usable | Inconsistent navigation, unclear error messages | Next release |
| Minor | Inconvenience | Redundant alt text, minor heading order issues | Backlog |

### Common Violations and Fixes

**Missing accessible name**
```html
<!-- Violation -->
<button><svg>...</svg></button>

<!-- Fix: aria-label -->
<button aria-label="Close dialog"><svg>...</svg></button>

<!-- Fix: visually hidden text -->
<button><span class="sr-only">Close dialog</span><svg>...</svg></button>
```

**Form label association**
```html
<!-- Violation -->
<label>Email</label>
<input type="email">

<!-- Fix: explicit association -->
<label for="email">Email</label>
<input type="email" id="email">

<!-- Fix: implicit association -->
<label>Email <input type="email"></label>
```

**Color contrast failure**
```
Minimum ratios (WCAG AA):
- Normal text (<18px or <14px bold): 4.5:1
- Large text (>=18px or >=14px bold): 3:1
- UI components and graphics: 3:1

Tools: WebAIM Contrast Checker, browser DevTools
```

**Focus visibility**
```css
/* Never do this without alternative */
:focus { outline: none; }

/* Proper custom focus */
:focus-visible {
  outline: 2px solid #005fcc;
  outline-offset: 2px;
}
```

## ARIA Decision Framework

```
Need to convey information to assistive technology?
|
+-- Can semantic HTML do it?
|   +-- YES: Use HTML (<button>, <nav>, <main>, <article>)
|   +-- NO: Continue to ARIA
|
+-- What type of ARIA needed?
    +-- Role: What IS this element? (role="dialog", role="tab")
    +-- State: What condition? (aria-expanded, aria-checked)
    +-- Property: What relationship? (aria-labelledby, aria-describedby)
    +-- Live region: Dynamic content? (aria-live="polite")
```

### ARIA Patterns for Common Widgets

**Disclosure (show/hide)**
```html
<button aria-expanded="false" aria-controls="content-1">
  Show details
</button>
<div id="content-1" hidden>
  Content here
</div>
```

**Tab interface**
```html
<div role="tablist" aria-label="Settings">
  <button role="tab" aria-selected="true" aria-controls="panel-1" id="tab-1">
    General
  </button>
  <button role="tab" aria-selected="false" aria-controls="panel-2" id="tab-2" tabindex="-1">
    Privacy
  </button>
</div>
<div role="tabpanel" id="panel-1" aria-labelledby="tab-1">...</div>
<div role="tabpanel" id="panel-2" aria-labelledby="tab-2" hidden>...</div>
```

**Modal dialog**
```html
<div role="dialog" aria-modal="true" aria-labelledby="dialog-title">
  <h2 id="dialog-title">Confirm action</h2>
  <p>Are you sure you want to proceed?</p>
  <button>Cancel</button>
  <button>Confirm</button>
</div>
```

## Keyboard Navigation Checklist

```
[ ] All interactive elements focusable with Tab
[ ] Focus order matches visual/logical order
[ ] Focus visible on all elements
[ ] No keyboard traps (can always Tab out)
[ ] Skip link as first focusable element
[ ] Escape closes modals/dropdowns
[ ] Arrow keys navigate within widgets (tabs, menus, grids)
[ ] Enter/Space activates buttons and links
[ ] Custom shortcuts documented and configurable
```

### Focus Management Patterns

**Modal focus trap**
```javascript
// On modal open:
// 1. Save previously focused element
// 2. Move focus to first focusable in modal
// 3. Trap Tab within modal boundaries

// On modal close:
// 1. Return focus to saved element
```

**Dynamic content**
```javascript
// After adding content:
// - Announce via aria-live region, OR
// - Move focus to new content heading

// After removing content:
// - Move focus to logical next element
// - Never leave focus on removed element
```

## Screen Reader Testing

### Announcement Verification

| Element | Should Announce |
|---------|-----------------|
| Button | Role + name + state ("Submit button") |
| Link | Name + "link" ("Home page link") |
| Image | Alt text OR "decorative" (skip) |
| Heading | Level + text ("Heading level 2, About us") |
| Form field | Label + type + state + instructions |
| Error | Error message + field association |

### Testing Commands (Quick Reference)

**VoiceOver (macOS)**
- VO = Ctrl + Option
- VO + A: Read all
- VO + Right/Left: Navigate elements
- VO + Cmd + H: Next heading
- VO + Cmd + J: Next form control

**NVDA (Windows)**
- NVDA + Down: Read all
- Tab: Next focusable
- H: Next heading
- F: Next form field
- B: Next button

## Automated Testing Integration

### axe-core in tests
```javascript
// jest-axe
import { axe, toHaveNoViolations } from 'jest-axe';
expect.extend(toHaveNoViolations);

test('component is accessible', async () => {
  const { container } = render(<MyComponent />);
  const results = await axe(container);
  expect(results).toHaveNoViolations();
});
```

### Lighthouse CI threshold
```javascript
// lighthouserc.js
module.exports = {
  assertions: {
    'categories:accessibility': ['error', { minScore: 90 / 100 }],
  },
};
```

## Remediation Priority Matrix

```
Impact vs Effort:
                    Low Effort    High Effort
High Impact     |   DO FIRST   |   PLAN NEXT   |
                |   alt text   |   redesign    |
                |   labels     |   nav rebuild |
----------------|--------------|---------------|
Low Impact      |   QUICK WIN  |   BACKLOG     |
                |   contrast   |   nice-to-have|
                |   tweaks     |   enhancements|
```

## Verification Checklist

Before marking accessibility work complete:

```
Automated Testing:
[ ] axe-core reports zero violations
[ ] Lighthouse accessibility >= 90
[ ] HTML validator passes (affects AT parsing)

Keyboard Testing:
[ ] Full task completion without mouse
[ ] Visible focus at all times
[ ] Logical tab order
[ ] No traps

Screen Reader Testing:
[ ] Tested with at least one screen reader (NVDA)
[ ] All content announced correctly
[ ] Interactive elements have roles/states
[ ] Dynamic updates announced

Visual Testing:
[ ] Contrast ratios verified (4.5:1 minimum)
[ ] Works at 200% zoom
[ ] No information conveyed by color alone
[ ] Respects prefers-reduced-motion
```

---
name: accessibility-expert
description: Tests and remediates accessibility issues for WCAG compliance and assistive technology compatibility. Use when (1) auditing UI for accessibility violations, (2) implementing keyboard navigation or screen reader support, (3) fixing color contrast or focus indicator issues, (4) ensuring form accessibility and error handling, (5) creating ARIA implementations.
---

# Accessibility Testing and Remediation

## Configuration

- **WCAG Level**: AA
- **Target Component**: Application
- **Compliance Standard**: WCAG 2.1
- **Testing Scope**: full-audit
- **Screen Reader**: NVDA

## WCAG 2.1 Quick Reference

### Compliance Levels
| Level | Requirement | Common Issues |
|-------|-------------|---------------|
| A | Minimum baseline | Missing alt text, no keyboard access, missing form labels |
| AA | Standard target | Contrast < 4.5:1, missing focus indicators, poor heading structure |
| AAA | Enhanced | Contrast < 7:1, sign language, extended audio description |

### Four Principles (POUR)
1. **Perceivable**: Content available to senses (alt text, captions, contrast)
2. **Operable**: UI navigable by all input methods (keyboard, touch, voice)
3. **Understandable**: Content and UI predictable and readable
4. **Robust**: Works with current and future assistive technologies

## Violation Severity Matrix

```
CRITICAL (fix immediately):
  - No keyboard access to interactive elements
  - Missing form labels
  - Images without alt text
  - Auto-playing audio without controls
  - Keyboard traps

HIGH (fix before release):
  - Contrast ratio below 4.5:1 (text) or 3:1 (large text)
  - Missing skip links
  - Incorrect heading hierarchy
  - Focus not visible
  - Missing error identification

MEDIUM (fix in next sprint):
  - Inconsistent navigation
  - Missing landmarks
  - Poor link text ("click here")
  - Missing language attribute
  - Complex tables without headers

LOW (backlog):
  - Timing adjustments
  - Multiple ways to find content
  - Context-sensitive help
```

## Testing Decision Tree

```
Start: What are you testing?
|
+-- New Component
|   +-- Has interactive elements? --> Keyboard Navigation Checklist
|   +-- Has text content? --> Check contrast + heading structure
|   +-- Has images? --> Verify alt text appropriateness
|   +-- Has forms? --> Form Accessibility Checklist
|
+-- Existing Page/Feature
|   +-- Run automated scan first (axe-core, Lighthouse)
|   +-- Manual keyboard walkthrough
|   +-- Screen reader verification
|   +-- Color contrast spot-check
|
+-- Third-party Widget
    +-- Check ARIA implementation
    +-- Verify keyboard support
    +-- Test with screen reader
    +-- Document limitations
```

## Keyboard Navigation Checklist

```markdown
[ ] All interactive elements reachable via Tab
[ ] Tab order follows visual/logical flow
[ ] Focus indicator visible (2px+ outline, 3:1 contrast)
[ ] No keyboard traps (can Tab out of all elements)
[ ] Skip link as first focusable element
[ ] Enter activates buttons and links
[ ] Space activates checkboxes and buttons
[ ] Arrow keys navigate within components (tabs, menus, radio groups)
[ ] Escape closes modals and dropdowns
[ ] Modals trap focus until dismissed
```

## Screen Reader Testing Patterns

### Essential Announcements to Verify
```
Interactive Elements:
  Button: "[label], button"
  Link: "[text], link"
  Checkbox: "[label], checkbox, [checked/unchecked]"
  Radio: "[label], radio button, [selected], [position] of [total]"
  Combobox: "[label], combobox, [collapsed/expanded]"

Dynamic Content:
  Loading: Use aria-busy="true" on container
  Status: Use role="status" for non-critical updates
  Alert: Use role="alert" for critical messages
  Live regions: aria-live="polite"

Forms:
  Required: "required" announced with label
  Invalid: "invalid entry" with error message
  Instructions: Announced with label via aria-describedby
```

### Testing Sequence
1. Navigate entire page with Tab key, listening to announcements
2. Test headings navigation (H key in screen reader)
3. Test landmark navigation (D key / rotor)
4. Test tables (T key, arrow keys within table)
5. Test forms (F key, complete form submission)
6. Test dynamic content updates (verify live regions)

## Color Contrast Requirements

| Text Type | Minimum Ratio | Enhanced (AAA) |
|-----------|---------------|----------------|
| Normal text (<18pt) | 4.5:1 | 7:1 |
| Large text (>=18pt or 14pt bold) | 3:1 | 4.5:1 |
| UI components & graphics | 3:1 | N/A |
| Focus indicators | 3:1 | N/A |

### Contrast Check Process
```
1. Identify all foreground/background color pairs
2. Calculate contrast ratio: (L1 + 0.05) / (L2 + 0.05)
   where L1 = lighter luminance, L2 = darker luminance
3. Common failures to check:
   - Placeholder text (often too light)
   - Disabled state (exempt but consider usability)
   - Links within text (must distinguish from text)
   - Error/success states on colored backgrounds
   - Text over images (use overlay or text shadow)
```

## ARIA Implementation Guide

### First Rule of ARIA
Use native HTML elements when possible. ARIA is for custom widgets only.

```html
<!-- WRONG: ARIA on native element -->
<div role="button" tabindex="0">Submit</div>

<!-- RIGHT: Native button -->
<button type="submit">Submit</button>
```

### When ARIA is Needed
```html
<!-- Custom tabs -->
<div role="tablist">
  <button role="tab" aria-selected="true" aria-controls="panel1">Tab 1</button>
  <button role="tab" aria-selected="false" aria-controls="panel2">Tab 2</button>
</div>
<div role="tabpanel" id="panel1">Content 1</div>
<div role="tabpanel" id="panel2" hidden>Content 2</div>

<!-- Expandable section -->
<button aria-expanded="false" aria-controls="content">Show details</button>
<div id="content" hidden>Expandable content</div>

<!-- Modal dialog -->
<div role="dialog" aria-modal="true" aria-labelledby="title">
  <h2 id="title">Dialog Title</h2>
  <!-- content -->
</div>

<!-- Live region for dynamic updates -->
<div aria-live="polite" aria-atomic="true">
  <!-- Status messages injected here -->
</div>
```

### Common ARIA Mistakes
```
- role="button" without keyboard support (Enter/Space)
- aria-label duplicating visible text
- aria-hidden="true" on focusable elements
- Missing aria-expanded on disclosure buttons
- Incorrect aria-controls reference
- Using aria-describedby for essential information
```

## Form Accessibility Patterns

### Required Form Structure
```html
<form>
  <!-- Explicit label association -->
  <label for="email">Email address</label>
  <input type="email" id="email" name="email"
         aria-required="true"
         aria-describedby="email-hint email-error">
  <span id="email-hint">We'll never share your email</span>
  <span id="email-error" role="alert"></span>

  <!-- Group related fields -->
  <fieldset>
    <legend>Shipping address</legend>
    <!-- address fields -->
  </fieldset>

  <!-- Clear submit button -->
  <button type="submit">Complete order</button>
</form>
```

### Error Handling Requirements
```
1. Identify the field in error (highlight + icon)
2. Describe the error in text (not just color)
3. Associate error with field (aria-describedby)
4. Announce error to screen readers (role="alert")
5. Move focus to first error on submit failure
6. Provide correction suggestions when possible
```

## Mobile Accessibility Checklist

```markdown
Touch Targets:
[ ] Minimum 44x44 CSS pixels
[ ] Adequate spacing between targets (8px+)
[ ] Touch action not dependent on gesture path

Gestures:
[ ] Alternative to multi-finger gestures
[ ] Alternative to path-based gestures (swipe)
[ ] Motion-based actions have alternatives

Screen Reader (iOS/Android):
[ ] accessibilityLabel set for images and icons
[ ] accessibilityHint for complex interactions
[ ] accessibilityRole matches element behavior
[ ] Focus order follows visual layout
```

## Automated Testing Integration

### Pre-commit Hook
```bash
#!/bin/bash
# Run axe-core on changed files
npx axe-core-cli --exit src/**/*.html

# Check for common issues
grep -r "onClick.*div\|onClick.*span" src/ && \
  echo "Warning: Click handler on non-interactive element" && exit 1
```

### CI Pipeline Checks
```yaml
accessibility-audit:
  script:
    - npx pa11y-ci --config .pa11yci.json
    - npx lighthouse --accessibility --output=json
  artifacts:
    paths:
      - accessibility-report.json
  rules:
    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
```

### Minimum CI Thresholds
```
axe-core: 0 critical violations, 0 serious violations
Lighthouse accessibility: >= 90
pa11y: 0 errors (warnings acceptable)
```

## Remediation Priority Framework

```
Priority 1 (This Sprint):
  - Blocks user task completion
  - Legal compliance risk
  - Affects many users

Priority 2 (Next Sprint):
  - Degrades experience significantly
  - Automated tools flag as error
  - Violates AA requirement

Priority 3 (Backlog):
  - Minor inconvenience
  - Violates AAA only
  - Affects edge cases

Priority 4 (Enhancement):
  - Improves usability for all
  - Best practice, not requirement
  - Future-proofing
```

## Verification Checklist

Before marking accessibility work complete:

```markdown
Automated:
[ ] axe-core: 0 violations
[ ] Lighthouse accessibility: 90+
[ ] HTML validation passes
[ ] No console accessibility warnings

Keyboard:
[ ] Complete all tasks keyboard-only
[ ] Focus visible at all times
[ ] Tab order logical
[ ] No keyboard traps

Screen Reader (test with at least one):
[ ] All content announced
[ ] Interactive elements labeled
[ ] Errors and updates announced
[ ] Navigation efficient

Visual:
[ ] All text passes contrast
[ ] UI components pass contrast
[ ] Works at 200% zoom
[ ] Works in high contrast mode
[ ] No seizure-inducing flashing

Forms:
[ ] All fields labeled
[ ] Errors identifiable
[ ] Required fields indicated
[ ] Instructions available
```

## Documentation Template

```markdown
# Accessibility Statement

## Conformance Status
This [website/application] is [fully/partially] conformant with WCAG 2.1 Level AA.

## Known Limitations
| Feature | Issue | Workaround | Timeline |
|---------|-------|------------|----------|
| [Feature] | [Description] | [Alternative] | [Fix date] |

## Assistive Technology Tested
- NVDA [version] with Firefox [version]
- VoiceOver with Safari [version]
- JAWS [version] with Chrome [version]

## Feedback
Contact [email] for accessibility issues.
Last updated: [date]
```

---
name: aws-cloud-expert
description: |
  Designs and implements AWS cloud architectures with focus on Well-Architected Framework, cost optimization, and security. Use when:
  1. Designing or reviewing AWS infrastructure architecture
  2. Migrating workloads to AWS or between AWS services
  3. Optimizing AWS costs (right-sizing, Reserved Instances, Savings Plans)
  4. Implementing AWS security, compliance, or disaster recovery
  5. Troubleshooting AWS service issues or performance problems
---

**Region**: us-east-1
**Secondary Region**: us-west-2
**Environment**: production
**VPC CIDR**: 10.0.0.0/16
**Instance Type**: t3.medium

# AWS Architecture Decision Framework

## Service Selection Matrix

| Workload Type | Primary Service | Alternative | Decision Factor |
|---------------|-----------------|-------------|-----------------|
| Stateless API | Lambda + API Gateway | ECS Fargate | Request duration >15min -> ECS |
| Stateful web app | ECS/EKS | EC2 Auto Scaling | Container expertise -> ECS/EKS |
| Batch processing | Step Functions + Lambda | AWS Batch | GPU/long-running -> Batch |
| Real-time streaming | Kinesis Data Streams | MSK (Kafka) | Existing Kafka -> MSK |
| Static website | S3 + CloudFront | Amplify | Full-stack -> Amplify |
| Relational DB | Aurora | RDS | High availability -> Aurora |
| Key-value store | DynamoDB | ElastiCache | Sub-ms latency -> ElastiCache |
| Data warehouse | Redshift | Athena | Ad-hoc queries -> Athena |

## Compute Decision Tree

```
Start: What's your workload pattern?
|
+-> Event-driven, <15min execution
|   +-> Lambda
|       Consider: Memory 512MB, concurrent executions, cold starts
|
+-> Long-running containers
|   +-> Need Kubernetes?
|       +-> Yes: EKS (managed) or self-managed K8s on EC2
|       +-> No: ECS Fargate (serverless) or ECS EC2 (cost optimization)
|
+-> GPU/HPC/Custom AMI required
|   +-> EC2 with appropriate instance family
|       g4dn/p4d (ML), c6i (compute), r6i (memory), i3en (storage)
|
+-> Batch jobs, queue-based
    +-> AWS Batch with Spot instances (up to 90% savings)
```

## Networking Architecture

### VPC Design Pattern

```
production VPC (10.0.0.0/16)
|
+-- Public Subnets (10.0.0.0/24, 10.0.1.0/24, 10.0.2.0/24)
|   +-- ALB, NAT Gateways, Bastion (if needed)
|
+-- Private Subnets (10.0.10.0/24, 10.0.11.0/24, 10.0.12.0/24)
|   +-- Application tier (ECS, EC2, Lambda VPC)
|
+-- Data Subnets (10.0.20.0/24, 10.0.21.0/24, 10.0.22.0/24)
    +-- RDS, ElastiCache, other data stores
```

### Security Group Rules

| Tier | Inbound From | Ports |
|------|--------------|-------|
| ALB | 0.0.0.0/0 | 443 |
| App | ALB SG | 8080 |
| Data | App SG | 5432 |

### VPC Endpoints (Cost Optimization)

Always create for high-traffic services:
- S3 Gateway Endpoint (free)
- DynamoDB Gateway Endpoint (free)
- Interface Endpoints: ECR, Secrets Manager, SSM, CloudWatch Logs

## Cost Optimization Checklist

### Immediate Actions (Week 1)
- [ ] Enable Cost Explorer and set up budgets with alerts
- [ ] Review and terminate unused resources (Cost Explorer idle resources report)
- [ ] Right-size EC2 instances (AWS Compute Optimizer recommendations)
- [ ] Delete unattached EBS volumes and old snapshots
- [ ] Review NAT Gateway data processing charges

### Cost Estimation Quick Reference

| Resource | Monthly Cost Estimate |
|----------|----------------------|
| t3.medium (on-demand) | ~$30 |
| t3.medium (1yr RI) | ~$18 |
| Lambda (1M invocations, 1s, 512MB) | ~$8 |
| RDS db.t3.medium (Multi-AZ) | ~$100 |
| Aurora Serverless v2 (8 ACU avg) | ~$350 |
| NAT Gateway + 100GB data | ~$50 |
| S3 (1TB Standard) | ~$23 |
| CloudFront (1TB transfer) | ~$85 |

## Security Implementation

### IAM Best Practices

```
Principle: Least privilege with explicit deny

1. Use IAM roles (not users) for applications
2. Require MFA for all human users
3. Use permission boundaries for delegated admin
4. Implement SCPs at Organization level
5. Regular access reviews with IAM Access Analyzer
```

### Example IAM Policy Pattern

```json
{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Sid": "AllowS3BucketAccess",
      "Effect": "Allow",
      "Action": ["s3:GetObject", "s3:PutObject"],
      "Resource": "arn:aws:s3:::my-bucket/*",
      "Condition": {
        "StringEquals": {"aws:PrincipalTag/Environment": "production"}
      }
    }
  ]
}
```

### Security Checklist

- [ ] Enable CloudTrail in all regions with log file validation
- [ ] Configure AWS Config rules for compliance monitoring
- [ ] Enable GuardDuty for threat detection
- [ ] Use Secrets Manager or Parameter Store for secrets (not env vars)
- [ ] Enable encryption at rest for all data stores
- [ ] Enforce TLS 1.2+ for all connections
- [ ] Implement VPC Flow Logs for network monitoring
- [ ] Use Security Hub for centralized security view

## High Availability Patterns

### Multi-AZ Architecture (99.99% target)

```
Region: us-east-1
|
+-- AZ-a                    +-- AZ-b                    +-- AZ-c
    |                           |                           |
    ALB (active)                ALB (active)                ALB (active)
    |                           |                           |
    ECS Tasks (2)  ECS Tasks (2)  ECS Tasks (2)
    |                           |                           |
    Aurora Writer               Aurora Reader               Aurora Reader
```

### Multi-Region Architecture (99.999% target)

```
Primary: us-east-1              Secondary: us-west-2
|                               |
Route 53 (failover routing)     Route 53 (health checks)
|                               |
CloudFront                      CloudFront
|                               |
Full stack                      Full stack (passive or active)
|                               |
Aurora Global Database -------> Aurora Read Replica
     (async replication)
```

### RTO/RPO Decision Matrix

| Tier | RTO Target | RPO Target | Strategy |
|------|------------|------------|----------|
| Tier 1 (Critical) | <15 min | <1 min | Multi-region active-active |
| Tier 2 (Important) | <1 hour | <15 min | Multi-region active-passive |
| Tier 3 (Standard) | <4 hours | <1 hour | Multi-AZ with cross-region backup |
| Tier 4 (Non-critical) | <24 hours | <24 hours | Single region, backup/restore |

## Monitoring and Observability

### CloudWatch Implementation

| Metric Type | Service | Key Metrics |
|-------------|---------|-------------|
| Compute | EC2/ECS | CPUUtilization, MemoryUtilization, NetworkIn/Out |
| Database | RDS/Aurora | DatabaseConnections, ReadLatency, WriteLatency |
| Serverless | Lambda | Duration, Errors, Throttles, ConcurrentExecutions |
| API | API Gateway | 4XXError, 5XXError, Latency, Count |
| Storage | S3 | BucketSizeBytes, NumberOfObjects, 4xxErrors |

### Alerting Thresholds

| Resource | Warning | Critical | Action |
|----------|---------|----------|--------|
| EC2 CPU | >70% 5min | >90% 5min | Scale out, investigate |
| RDS CPU | >80% 5min | >95% 5min | Scale up, query optimization |
| Lambda errors | >1% | >5% | Investigate, rollback |
| ALB 5xx | >0.1% | >1% | Investigate backend |
| DynamoDB throttle | Any | Sustained | Increase capacity |

## Verification Checklist

### Before Production Launch

- [ ] Well-Architected Review completed (all 6 pillars)
- [ ] Load testing completed with expected peak + 50% headroom
- [ ] Disaster recovery tested with documented RTO/RPO
- [ ] Security assessment passed (penetration test if required)
- [ ] Compliance controls verified (if applicable)
- [ ] Monitoring dashboards and alerts configured
- [ ] Runbooks documented for common operations
- [ ] Cost projection validated and budgets set
- [ ] Tagging strategy implemented for all resources
- [ ] Backup and restore procedures tested

---
name: ast-code-analysis-superpower
description: AST-based code pattern analysis using ast-grep for security, performance, and structural issues. Use when (1) reviewing code for security vulnerabilities, (2) analyzing React hook dependencies or performance patterns, (3) detecting structural anti-patterns across large codebases, (4) needing systematic pattern matching beyond manual inspection.
---

# AST-Grep Code Analysis

AST pattern matching identifies code issues through structural recognition rather than line-by-line reading. Code structure reveals hidden relationships, vulnerabilities, and anti-patterns that surface inspection misses.

## Configuration

- **Target Language**: javascript
- **Analysis Focus**: security
- **Severity Level**: ERROR
- **Framework**: React
- **Max Nesting Depth**: 3

## Prerequisites

```bash
# Install ast-grep (if not available)
npm install -g @ast-grep/cli
# Or: mise install -g ast-grep
```

## Decision Tree: When to Use AST Analysis

```
Code review needed?
|
+-- Simple code (<50 lines, obvious structure) --> Manual review
|
+-- Complex code (nested, multi-file, abstraction layers)
    |
    +-- Security review required? --> Use security patterns
    +-- Performance analysis? --> Use performance patterns
    +-- Structural quality? --> Use structure patterns
    +-- Cross-file patterns? --> Run with --include glob
```

## Pattern Categories

| Category | Focus | Common Findings |
|----------|-------|-----------------|
| Security | Crypto functions, auth flows | Hardcoded secrets, weak tokens |
| Performance | Hooks, loops, async | Infinite re-renders, memory leaks |
| Structure | Nesting, complexity | Deep conditionals, maintainability |

## Essential Patterns

### Security: Hardcoded Secrets

```yaml
# sg-rules/security/hardcoded-secrets.yml
id: hardcoded-secrets
language: javascript
rule:
  pattern: |
    const $VAR = '$LITERAL';
    $FUNC($VAR, ...)
  meta:
    severity: ERROR
    message: "Potential hardcoded secret detected"
```

### Security: Insecure Token Generation

```yaml
# sg-rules/security/insecure-tokens.yml
id: insecure-token-generation
language: javascript
rule:
  pattern: |
    btoa(JSON.stringify($OBJ) + '.' + $SECRET)
  meta:
    severity: ERROR
    message: "Insecure token generation using base64"
```

### Performance: React Hook Dependencies

```yaml
# sg-rules/performance/react-hook-deps.yml
id: react-hook-dependency-array
language: typescript
rule:
  pattern: |
    useEffect(() => {
      $BODY
    }, [$FUNC])
  meta:
    severity: WARNING
    message: "Function dependency may cause infinite re-renders"
```

### Structure: Deep Nesting

```yaml
# sg-rules/structure/deep-nesting.yml
id: deep-nesting
language: javascript
rule:
  any:
    - pattern: |
        if ($COND1) {
          if ($COND2) {
            if ($COND3) {
              $BODY
            }
          }
        }
    - pattern: |
        for ($INIT) {
          for ($INIT2) {
            for ($INIT3) {
              $BODY
            }
          }
        }
  meta:
    severity: WARNING
    message: "Deep nesting (>3 levels) - consider refactoring"
```

## Running Analysis

```bash
# Security scan
ast-grep run -r sg-rules/security/

# Performance scan on React files
ast-grep run -r sg-rules/performance/ --include="*.tsx,*.jsx"

# Full scan with JSON output
ast-grep run -r sg-rules/ --format=json > analysis-report.json

# Interactive mode for investigation
ast-grep run -r sg-rules/ --interactive
```

## Pattern Writing Checklist

- [ ] Pattern matches specific anti-pattern, not general code
- [ ] Uses `inside` or `has` for context constraints
- [ ] Includes `not` constraints to reduce false positives
- [ ] Separate rules per language (JS vs TS)
- [ ] Appropriate severity (ERROR/WARNING/INFO)

## Common Mistakes

| Mistake | Symptom | Fix |
|---------|---------|-----|
| Too generic patterns | Many false positives | Add context constraints |
| Missing `inside` | Matches wrong locations | Scope with parent context |
| No `not` clauses | Matches valid patterns | Exclude known-good cases |
| JS patterns on TS | Type annotations break match | Create language-specific rules |

## Verification Steps

1. **Test pattern accuracy**: Run on known-vulnerable code samples
2. **Check false positive rate**: Review first 10 matches manually
3. **Validate severity**: Confirm ERROR-level findings are actionable
4. **Cross-file coverage**: Verify pattern runs across intended scope

## Example Output

```
$ ast-grep run -r sg-rules/
src/components/UserProfile.jsx:15: ERROR [insecure-tokens] Insecure token generation
src/hooks/useAuth.js:8: ERROR [hardcoded-secrets] Potential hardcoded secret
src/components/Dashboard.tsx:23: WARNING [react-hook-deps] Function dependency
src/utils/processData.js:45: WARNING [deep-nesting] Deep nesting detected

Found 4 issues (2 errors, 2 warnings)
```

## Project Setup

```bash
# Initialize ast-grep in project
ast-grep init

# Create rule directories
mkdir -p sg-rules/{security,performance,structure}

# Add to CI pipeline
# .github/workflows/lint.yml
# - run: ast-grep run -r sg-rules/ --format=json
```

## Custom Pattern Templates

### React Specific Patterns

```yaml
# Missing key in list rendering
id: missing-list-key
language: typescript
rule:
  pattern: |
    $ARRAY.map(($ITEM) => <$COMPONENT $$$PROPS />)
  constraints:
    $PROPS:
      not:
        has:
          pattern: 'key={$_}'
  meta:
    severity: WARNING
    message: "Missing key prop in list rendering"
```

### Async/Await Patterns

```yaml
# Missing error handling in async
id: unhandled-async
language: javascript
rule:
  pattern: |
    async function $NAME($$$) {
      $$$BODY
    }
  constraints:
    $BODY:
      not:
        has:
          pattern: 'try { $$$ } catch'
  meta:
    severity: WARNING
    message: "Async function without try-catch error handling"
```

## Integration with CI/CD

```yaml
# GitHub Actions example
name: AST Analysis
on: [push, pull_request]
jobs:
  analyze:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Install ast-grep
        run: npm install -g @ast-grep/cli
      - name: Run analysis
        run: |
          ast-grep run -r sg-rules/ --format=json > report.json
          if grep -q '"severity": "ERROR"' report.json; then
            echo "Critical issues found!"
            exit 1
          fi
```

---
name: project-evaluation-for-production-decision
description: A skill for evaluating projects to determine if they are ready for production, considering technical, formal, and practical aspects.
---

# Project Evaluation for Production Decision

Act as a Project Evaluation Specialist. You are responsible for assessing projects to determine their readiness for production.

Your task is to evaluate the project on three fronts:
1. Technical Evaluation:
   - Assess the technical feasibility and stability.
   - Evaluate code quality and system performance.
   - Ensure compliance with technical specifications.

2. Formal Evaluation:
   - Review documentation and adherence to formal processes.
   - Check for completeness of requirements and deliverables.
   - Validate alignment with business goals.

3. Practical Evaluation:
   - Test usability and user experience.
   - Consider practical deployment issues and risks.
   - Ensure the project meets practical use-case scenarios.

You will:
- Provide a comprehensive report on each evaluation aspect.
- Offer a final recommendation: Go or No-Go for production.

Variables:
- projectName - The name of the project being evaluated.
- evaluationDate - The date of the evaluation.

---
name: extract-query-conditions
description: A skill to extract and transform filter and search parameters from Azure AI Search request JSON into a structured list format.
---

# Extract Query Conditions

Act as a JSON Query Extractor. You are an expert in parsing and transforming JSON data structures. Your task is to extract the filter and search parameters from a user's Azure AI Search request JSON and convert them into a list of objects with the format [{name: parameter, value: parameterValue}].

You will:
- Parse the input JSON to locate filter and search components.
- Extract relevant parameters and their values.
- Format the output as a list of dictionaries with 'name' and 'value' keys.

Rules:
- Ensure all extracted parameters are accurately represented.
- Maintain the integrity of the original data structure while transforming it.

Example:
Input JSON:
{
  "filter": "category eq 'books' and price lt 10",
  "search": "adventure"
}

Output:
[
  {"name": "category", "value": "books"},
  {"name": "price", "value": "lt 10"},
  {"name": "search", "value": "adventure"}
]

---
name: web-application-testing-skill
description: A toolkit for interacting with and testing local web applications using Playwright.
---

# Web Application Testing

This skill enables comprehensive testing and debugging of local web applications using Playwright automation.

## When to Use This Skill

Use this skill when you need to:
- Test frontend functionality in a real browser
- Verify UI behavior and interactions
- Debug web application issues
- Capture screenshots for documentation or debugging
- Inspect browser console logs
- Validate form submissions and user flows
- Check responsive design across viewports

## Prerequisites

- Node.js installed on the system
- A locally running web application (or accessible URL)
- Playwright will be installed automatically if not present

## Core Capabilities

### 1. Browser Automation
- Navigate to URLs
- Click buttons and links
- Fill form fields
- Select dropdowns
- Handle dialogs and alerts

### 2. Verification
- Assert element presence
- Verify text content
- Check element visibility
- Validate URLs
- Test responsive behavior

### 3. Debugging
- Capture screenshots
- View console logs
- Inspect network requests
- Debug failed tests

## Usage Examples

### Example 1: Basic Navigation Test
```javascript
// Navigate to a page and verify title
await page.goto('http://localhost:3000');
const title = await page.title();
console.log('Page title:', title);
```

### Example 2: Form Interaction
```javascript
// Fill out and submit a form
await page.fill('#username', 'testuser');
await page.fill('#password', 'password123');
await page.click('button[type="submit"]');
await page.waitForURL('**/dashboard');
```

### Example 3: Screenshot Capture
```javascript
// Capture a screenshot for debugging
await page.screenshot({ path: 'debug.png', fullPage: true });
```

## Guidelines

1. **Always verify the app is running** - Check that the local server is accessible before running tests
2. **Use explicit waits** - Wait for elements or navigation to complete before interacting
3. **Capture screenshots on failure** - Take screenshots to help debug issues
4. **Clean up resources** - Always close the browser when done
5. **Handle timeouts gracefully** - Set reasonable timeouts for slow operations
6. **Test incrementally** - Start with simple interactions before complex flows
7. **Use selectors wisely** - Prefer data-testid or role-based selectors over CSS classes

## Common Patterns

### Pattern: Wait for Element
```javascript
await page.waitForSelector('#element-id', { state: 'visible' });
```

### Pattern: Check if Element Exists
```javascript
const exists = await page.locator('#element-id').count() > 0;
```

### Pattern: Get Console Logs
```javascript
page.on('console', msg => console.log('Browser log:', msg.text()));
```

### Pattern: Handle Errors
```javascript
try {
  await page.click('#button');
} catch (error) {
  await page.screenshot({ path: 'error.png' });
  throw error;
}
```

## Limitations

- Requires Node.js environment
- Cannot test native mobile apps (use React Native Testing Library instead)
- May have issues with complex authentication flows
- Some modern frameworks may require specific configuration