Generate a tailored intelligence briefing for defense-focused computer vision researchers, emphasizing Edge AI and threat detection innovations.
1{2 "opening": "",3 "criticalIntelligence": [4 {5 "headline": "",6 "source": "",7 "technicalSummary": "",8 "relevanceScore": "",9 "actionableInsight": ""10 },11 {12 "headline": "",13 "source": "",14 "technicalSummary": "",15 "relevanceScore": "",16 "actionableInsight": ""17 },18 // Add up to 8 total items19 ],20 "technicalDeepDive": [21 {22 "breakthroughItem": "",23 "implementationDetails": ""24 },25 {26 "breakthroughItem": "",27 "implementationDetails": ""28 }29 // Add up to 3 items30 ],31 "priorityIntelligenceTargets": {32 "primary": [33 "False positive reduction methodologies",34 "Edge AI optimization for resource-constrained hardware",35 "Real-time inference benchmarks"36 ],37 "secondary": [38 "Defense procurement announcements",39 "SBIR/STTR opportunities",40 "Counter-UAS technologies"41 ],42 "tertiary": [43 "PyTorch/OpenCV updates",44 "Rust embedded frameworks",45 "Military robotics contracts"46 ]47 },48 "sourcesToPrioritize": [49 "arXiv (cs.CV, cs.RO, cs.LG)",50 "Breaking Defense",51 "The War Zone",52 "NVIDIA Developer Blog"53 ],54 "exclusions": [55 "Consumer tech unless directly applicable",56 "Theoretical papers without implementation paths",57 "Rehashed news",58 "General AI hype without substance"59 ],60 "enhancedFeatures": {61 "benchmarkComparisonTables": true,62 "reproducibleResearchLinks": true,63 "conferenceDeadlines": true,64 "defenseContractAwards": true,65 "weeklyTrendChart": true66 }67}
Protect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses, and enforce token budget rate limits to control costs. Use this skill when the user is building or securing any endpoint that processes user prompts with an LLM, even if they describe it as "preventing jailbreaks," "stopping prompt attacks," "blocking sensitive data," or "controlling AI API costs" rather than naming specific protections.
Symmetry-Driven Decision Architecture - A resonance-guided thinking partner that stabilizes complex ideas into clear next steps.
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.
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.