/ 目录 / 演练场 / skill-optimizer
← 全部服务器 ↗ GitHub
● 社区 hqhq1025 ⚡ 即开即用

skill-optimizer

作者 hqhq1025 · hqhq1025/skill-optimizer

Audit a single SKILL.md using real session data plus static analysis — tells you exactly what to change.

skill-optimizer looks at a SKILL.md through two lenses: (1) session logs — did it activate when expected, was the output useful — and (2) static analysis — is the frontmatter clean, is the description properly intent-scoped, are examples calibrated. It outputs concrete edits you can apply. Pairs well with SkillCompass (which does bundle-level ranking).

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

skill-optimizer-skill.replay ▶ 就绪
0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： skill-optimizer

How to diagnose and fix one underperforming skill

👤 Skill authors iterating on a specific skill ⏱ ~30 min intermediate

何时使用： You notice one skill never activates, or activates wrongly.

步骤
  1. Review the patch
    Show me the proposed SKILL.md diff.✓ 已复制
    → Minimal, reviewable diff
  2. Apply and validate
    Apply the patch and tell me what to watch for this week.✓ 已复制
    → Validation checklist

结果： A targeted improvement with an accountability plan.

注意事项
  • Optimizing for activation rate but breaking scope — Include a 'false positive rate' acceptance metric
搭配使用： skillcompass-skill

Polish your first SKILL.md before publishing

👤 First-time skill authors ⏱ ~20 min beginner

何时使用： You wrote a SKILL.md and want expert review before shipping.

步骤
  1. Ask for a review
    Review my SKILL.md against skill-optimizer's static checks.✓ 已复制
    → Checklist with pass/fail + rationale
  2. Fix issues
    Apply the fixes and show me the final version.✓ 已复制
    → Clean SKILL.md

结果： A ship-ready SKILL.md.

注意事项
  • Over-promising in the description — Be specific about what the skill does; Claude uses it to decide activation

组合

与其他 MCP 搭配，撬动十倍杠杆

skill-optimizer-skill + skillcompass-skill

SkillCompass ranks the bundle; skill-optimizer dives into the worst offender

Use SkillCompass to pick the weakest skill, then optimize its SKILL.md.✓ 已复制
skill-optimizer-skill + filesystem

Apply SKILL.md patches directly

Apply the proposed diff to ~/.claude/skills/my-skill/SKILL.md.✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
static-analysis SKILL.md path Before publishing or during iteration 0
log-based-analysis logs + skill path Post-use tuning 0
patch-generation findings After analysis 0

成本与限制

运行它的成本

API 配额
none beyond LLM
每次调用 Token 数
2–10k per skill analysis
费用
free
提示
Static analysis is nearly free; log analysis costs more — run it only when iterating

安全

权限、密钥、影响范围

凭据存储： none; logs may contain sensitive prompts — treat their path carefully
数据出站： none

故障排查

常见错误与修复

No logs found

Confirm Claude Code trace path; pass the path explicitly if non-default.

Suggestions conflict with intended scope

Tell the optimizer your scope constraints; it can respect non-goals

替代方案

skill-optimizer 对比其他方案

替代方案何时用它替代权衡
skillcompass-skillYou need bundle-level ranking, not single-skill depthBreadth over depth

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills