一键导入
evolve-skill
Analyze feedback and evolve skills through structured improvement. The meta-skill that makes other skills better.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Analyze feedback and evolve skills through structured improvement. The meta-skill that makes other skills better.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Scaffold a new Express API endpoint with controller, route (OpenAPI annotations), response type, and barrel exports.
Low-level Cardano utilities with @meshsdk/core-cst
Cardano transaction building with @meshsdk/transaction
Cardano wallet integration with @meshsdk/wallet
Scaffold a new cron job with in-process guard, env-configurable schedule, SyncStatus DB locking, and job registry wiring.
Scaffold a new Prisma database model with project conventions (snake_case mapping, BigInt for lovelace, timestamps, relations).
Analyze feedback and improve skills through structured evolution. This meta-skill enables skills to learn and improve over time.
$0 - Skill name to evolve (e.g., add-chart)--all - Analyze all skills--analyze-only {skill} - Just show analysis, no changesrollback {skill} - Rollback to previous versionrollback {skill} {version} - Rollback to specific versionversions {skill} - List available versionsRead all feedback files for the target skill:
.claude/skills/.feedback/${$0}/*.yaml
Parse each feedback file and aggregate:
Categorize improvements by type:
Look for patterns:
Present proposals to the user using AskUserQuestion:
Based on {N} feedback entries for '{skill-name}':
- Success rate: {X}%
- Common corrections: {list}
- Common suggestions: {list}
Proposed improvements:
1. {Improvement 1} - rationale from feedback
2. {Improvement 2} - rationale from feedback
...
Which improvements should we apply?
Options should include:
For each approved improvement:
Save current version to .versions/
cp SKILL.md .versions/{current-version}.md
Edit SKILL.md with the improvement
Update metadata:
version: {new-version} # Bump appropriately
last-evolved: {today's date}
evolution-count: {previous + 1}
Update CHANGELOG.md:
## [{new-version}] - {date}
### Changed
- {Description of change 1}
- {Description of change 2}
### Feedback-driven
Based on {N} feedback entries. Key patterns addressed:
- {Pattern 1}
- {Pattern 2}
Create a git commit with:
git add .claude/skills/${$0}/
git commit -m "evolve(${$0}): {brief description}
Based on {N} feedback entries:
- {Key improvement 1}
- {Key improvement 2}
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"
Tell the user:
/skill-name to verifyrollback {skill} - Previous Version.versions/revert(${skill}): rollback to {version}rollback {skill} {version} - Specific Version.versions/{version}.mdversions {skill}.versions/ directoryOutput format:
Versions for '{skill}':
1.0.0 - 2026-02-02 - Initial release
1.1.0 - 2026-02-15 - Added ErrorBoundary pattern (current)
--allOutput format:
Skill Evolution Status:
add-chart - 5 feedback entries, 60% success, needs evolution
add-api-route - 2 feedback entries, 100% success, healthy
add-dashboard - 0 feedback entries, no data
...
Recommend which skills to evolve first.
Use semantic versioning:
Patch (1.0.x) - Small fixes, clarifications
Minor (1.x.0) - New content, significant improvements
Major (x.0.0) - Breaking changes (rare for skills)
# If corrections mention "order" or "sequence"
corrections:
- "Had to reorder the steps"
- "Step 3 should come before Step 2"
→ Instruction ordering issue
# If corrections mention specific code
corrections:
- "Fixed import order"
- "Added missing ErrorBoundary"
→ Template needs updating
# If suggestions mention "add" or "include"
suggestions:
- "Add section about error handling"
- "Include z-index best practices"
→ Missing documentation
After evolution:
.versions/last-evolved date updatedevolution-count incrementedAfter rollback: