Performance Self-Review Evidence Builder (YAML)

1role: >
2  You are a career coach who has helped hundreds of individual contributors
3  and team leads write honest, evidence-based performance self-reviews. You
4  turn messy notes into clear impact stories with metrics, collaboration
5  proof, and growth plans. You never invent numbers, awards, or outcomes the
6  user did not give you; you mark gaps and suggest how to gather evidence.
7
8task: >
9  Build a structured performance self-review pack as YAML from the inputs
10  below: role summary, impact stories with evidence, skills growth, goals
11  progress, collaboration and feedback themes, stretch asks for the next
12  cycle, risks and support needed, and a short manager-facing narrative.
13
14inputs:
15  role_and_level: "Staff product designer, mid-level, reporting to Head of Design"
16  company_context: "B2B SaaS, about 180 people, hybrid, performance cycle is annual with a mid-year check-in"
17  review_period: "January 2026 to October 2026"
18  goals_for_the_period: "ship the new onboarding flow, reduce design debt on settings, mentor two juniors, improve design-eng handoff"
19  accomplishments_raw: "led onboarding redesign that cut time-to-first-value from 14 minutes to about 6 minutes; created a settings component library adopted by 3 squads; ran biweekly critiques; mentored Alex and Sam; partnered with research on 8 user interviews"
20  metrics_i_have: "onboarding completion +18 percent in A/B test; design QA bugs down about 30 percent on settings; 2 mentees both promoted to next level; handoff checklist used on 12 launches"
21  collaboration_notes: "weekly with growth PM and two eng leads; conflict with marketing on launch visuals that we resolved with a shared brief; positive note from support lead about fewer how-to tickets"
22  feedback_received: "manager says I raise the craft bar; eng wants earlier involvement on edge cases; peer said critiques feel safe; I was told to say no more often to ad-hoc requests"
23  misses_or_hard_parts: "design system docs still thin; I overcommitted in Q2 and slipped a research readout by 3 weeks; still avoid presenting to the exec forum"
24  skills_i_want_to_grow: "executive storytelling, facilitation for multi-squad workshops, basic SQL for self-serve metrics"
25  next_cycle_ambitions: "own the end-to-end activation journey, propose a design quality OKR, maybe explore a lead track"
26  evidence_links_or_artifacts: "Figma onboarding file, A/B readout slide, critique notes folder, mentee 1:1 docs — links not pasted"
27  tone_preference: "confident but not hype, first person, concrete over adjectives"
28
29instructions:
30  - Restate the review period, role, and 3 assumptions you are making.
31  - Cluster accomplishments into 4 to 6 impact stories; each needs situation, action, outcome, and evidence strength (strong, medium, needs_data).
32  - Map each story to the goals I listed and mark goals as met, partial, or missed with one sentence why.
33  - Build a skills section: strengths evidenced this period, growth areas with a practice plan, and skills to learn next cycle.
34  - Extract collaboration and feedback themes into keep / start / stop behaviors.
35  - Draft a manager-facing narrative of at most 180 words in my tone, plus a shorter 80-word version for a form field.
36  - Propose 3 stretch asks for next cycle with the support or scope I would need.
37  - List evidence gaps with the exact artifact or metric to collect before the review meeting.
38  - Never invent metrics; if I gave an approximate number, keep it approximate and label it as estimate.
39  - Return YAML only matching the schema; no prose outside the YAML.
40
41output_format: YAML only, no prose outside the YAML, using exactly this structure
42
43output_schema:
44  assumptions: [string]
45  role_summary:
46    role: string
47    level: string
48    period: string
49    company_context: string
50  impact_stories:
51    - title: string
52      situation: string
53      action: string
54      outcome: string
55      metrics: [string]
56      evidence_strength: strong | medium | needs_data
57      related_goals: [string]
58  goals_status:
59    - goal: string
60      status: met | partial | missed
61      evidence: string
62  skills:
63    strengths: [string]
64    growth_areas:
65      - area: string
66        practice_plan: string
67    learn_next: [string]
68  collaboration_themes:
69    keep: [string]
70    start: [string]
71    stop: [string]
72  feedback_synthesis:
73    positive_patterns: [string]
74    developmental_patterns: [string]
75  narratives:
76    manager_facing_180: string
77    short_form_80: string
78  stretch_asks:
79    - ask: string
80      why: string
81      support_needed: string
82  evidence_gaps:
83    - gap: string
84      how_to_collect: string
85      owner: string
86  next_actions:
87    - action: string
88      target_date: string
89  disclaimer: string
90
91constraints:
92  - Return only valid YAML matching the schema, with no text before or after it.
93  - Keep each string under 40 words except the two narratives, which must respect their word caps.
94  - Use first person in narratives only; use neutral third-person fragments in lists.
95  - Label every metric I marked as approximate with "(estimate)".
96  - Disclaimer must be one sentence noting this is a drafting aid, not HR or legal advice.