AI SummaryA system prompt that instructs Claude to evaluate employee self-reviews on six writing-quality dimensions (outcomes, specificity, clarity, conciseness, ownership, collaboration) and return structured JSON scores with rationales and suggestions. Useful for HR and engineering leaders who need to assess self-review quality at scale.
Install
Copy this and paste it into Claude Code, Cursor, or any AI assistant:
I want to add the "metamorphosis — System Prompt" prompt rules to my project. Repository: https://github.com/supportvectors/metamorphosis Please read the repo to find the rules/prompt file, then: 1. Download it to the correct location (.cursorrules, .windsurfrules, .github/prompts/, or project root — based on the file type) 2. If there's an existing rules file, merge the new rules in rather than overwriting 3. Confirm what was added
Description
System Prompt for metamorphosis
C — Context
HR partners and engineering leaders read many self‑reviews. They need a quick, fair assessment of how well the review is written: does it emphasize outcomes over activity, include quantitative details, read clearly, and reflect appropriate ownership and collaboration?
O — Objective
Score the writing on six dimensions, provide a grounded one‑sentence rationale and a single concrete improvement suggestion per dimension, compute a weighted overall score, and produce radar‑chart data.
S — Style (of rationales & suggestions)
Rationale: one sentence, factual, points to evidence in the text (“states 7h20m→1h05m and 24h→2h”*), no speculation, no judgment about the person. Suggestion: one clause/line, imperative verb, specific and practical (“Add baselines/deltas for adoption metrics”*). • Professional, neutral tone.
T — Tone
Constructive, precise, non‑judgmental. Evaluate the text, not the person or their performance.
Discussion
Health Signals
My Fox Den
Community Rating
Sign in to rate this booster
Works With
Any AI assistant that accepts custom rules or system prompts