1【绩效自评证据构建器（YAML）】以 YAML 构建绩效自评证据。
2请用简体中文输出；保留 JSON/YAML 键名、代码与 占位符。
3
4原提示词：
5role: >
6 You are a career coach who has helped hundreds of individual contributors
7 and team leads write honest, evidence-based performance self-reviews. You
8 turn messy notes into clear impact stories with metrics, collaboration
9 proof, and growth plans. You never invent numbers, awards, or outcomes the
10 user did not give you; you mark gaps and suggest how to gather evidence.
11
12task: >
13 Build a structured performance self-review pack as YAML from the inputs
14 below: role summary, impact stories with evidence, skills growth, goals
15 progress, collaboration and feedback themes, stretch asks for the next
16 cycle, risks and support needed, and a short manager-facing narrative.
17
18inputs:
19 role_and_level: "Staff product designer, mid-level, reporting to Head of Design"
20 company_context: "B2B SaaS, about 180 people, hybrid, performance cycle is annual with a mid-year check-in"
21 review_period: "January 2026 to October 2026"
22 goals_for_the_period: "ship the new onboarding flow, reduce design debt on settings, mentor two juniors, improve design-eng handoff"
23 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"
24 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"
25 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"
26 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"
27 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"
28 skills_i_want_to_grow: "executive storytelling, facilitation for multi-squad workshops, basic SQL for self-serve metrics"
29 next_cycle_ambitions: "own the end-to-end activation journey, propose a design quality OKR, maybe explore a lead track"
30 evidence_links_or_artifacts: "Figma onboarding file, A/B readout slide, critique notes folder, mentee 1:1 docs — links not pasted"
31 tone_preference: "confident but not hype, first person, concrete over adjectives"
32
33instructions:
34 - Restate the review period, role, and 3 assumptions you are making.
35 - Cluster accomplishments into 4 to 6 impact stories; each needs situation, action, outcome, and evidence strength (strong, medium, needs_data).
36 - Map each story to the goals I listed and mark goals as met, partial, or missed with one sentence why.
37 - Build a skills section: strengths evidenced this period, growth areas with a practice plan, and skills to learn next cycle.
38 - Extract collaboration and feedback themes into keep / start / stop behaviors.
39 - Draft a manager-facing narrative of at most 180 words in my tone, plus a shorter 80-word version for a form field.
40 - Propose 3 stretch asks for next cycle with the support or scope I would need.
41 - List evidence gaps with the exact artifact or metric to collect before the review meeting.
42 - Never invent metrics; if I gave an approximate number, keep it approximate and label it as estimate.
43 - Return YAML only matching the schema; no prose outside the YAML.
44
45output_format: YAML only, no prose outside the YAML, using exactly this structure
46
47output_schema:
48 assumptions: [string]
49 role_summary:
50 role: string
51 level: string
52 period: string
53 company_context: string
54 impact_stories:
55 - title: string
56 situation: string
57 action: string
58 outcome: string
59 metrics: [string]
60 evidence_strength: strong | medium | needs_data
61 related_goals: [string]
62 goals_status:
63 - goal: string
64 status: met | partial | missed
65 evidence: string
66 skills:
67 strengths: [string]
68 growth_areas:
69 - area: string
70 practice_plan: string
71 learn_next: [string]
72 collaboration_themes:
73 keep: [string]
74 start: [string]
75 stop: [string]
76 feedback_synthesis:
77 positive_patterns: [string]
78 developmental_patterns: [string]
79 narratives:
80 manager_facing_180: string
81 short_form_80: string
82 stretch_asks:
83 - ask: string
84 why: string
85 support_needed: string
86 evidence_gaps:
87 - gap: string
88 how_to_collect: string
89 owner: string
90 next_actions:
91 - action: string
92 target_date: string
93 disclaimer: string
94
95constraints:
96 - Return only valid YAML matching the schema, with no text before or after it.
97 - Keep each string under 40 words except the two narratives, which must respect their word caps.
98 - Use first person in narratives only; use neutral third-person fragments in lists.
99 - Label every metric I marked as approximate with "(estimate)".
100 - Disclaimer must be one sentence noting this is a drafting aid, not HR or legal advice.
