skill-audit
Skill1 starsChanged 7 months agoMITView on GitHub
小能核心技能 — 使用 SMS v1.0 十维雷达评估体系对 Skill 进行质量审计,输出结构化评估报告。触发词:审计技能 / 评估 XX 的质量 / 小能评分 / audit skill / 十维评估
64 other projects use a version of this.
Adopted by
Most recently taken up by
- GravionLabs/skillstheir own version, first seen Nov 15, 2026
- DancinGhost/agent-metaskillstheir own version, first seen Nov 15, 2026
- vlad-ryzhkov/ai-context-engineering-for-frontendtheir own version, first seen Nov 15, 2026
- macintog/skillstheir own version, first seen Nov 15, 2026
- automagik-si/genietheir own version, first seen Nov 15, 2026
- aditya-vermax/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use root-cause, write-a-skill and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Ingramradical235Skillroot-cause
Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.
Also in 3 projects that use this
simo97Skillwrite-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Also in 4 projects that use this
Microsoft AzureSkillreflect
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
Also in 5 projects that use this
sunnyclinches44Skillexplain
Explains code using real-world analogies and ASCII diagrams
Also in 4 projects that use this
eherrerosjSkillhumanize
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Triggers on: 'humanize', 'make this sound human', 'remove AI writing', 'de-AI', 'sound more natural', 'less robotic', 'too AI-sounding', or when reviewing text that reads like AI output.
Also in 3 projects that use this
MicrosoftSkillreport
Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.
Also in 3 projects that use this
Other versions64 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 64
- nyldn/claude-octopus★ 4.4ksame name
- automagik-si/genie★ 353same name
- automagik-dev/genie★ 351same name
- namastexlabs/automagik-genie★ 351same name
- Rtur2003/Claude-Code-Promts-Skills★ 53same name
- fimoklei/pm-ai-playbook★ 42same name
- cth9191/skill-audit★ 23same name
- anysiteio/agent-skills★ 20same name
- okjpg/skill-audit★ 15same name
- macintog/codex-spine★ 12same name
54 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- 小能Skill
- agent-capability-mapSkill
- skill-card-genSkill
- skill-forgeSkill
- skill-graphSkill
- skill-registry-scanSkill
The file
Files
Skill Audit(十维质量审计)
v2.0 | 2026-04-25 升级:从 6 维评分升级为 SMS v1.0 十维雷达
流程
Step 1:读取 SKILL.md
读取目标 Skill 的完整 SKILL.md 内容。如果超过 500 行,分段读取。
Step 2:填写 Skill Card 元数据
先确认以下基本信息:
skill_id: "SK-{领域}-{序号}"
name_zh: ""
version: ""
owner: ""
parent_agent: "" # 归属 Agent
type_primary: "" # 12 类之一
type_secondary: ""
maturity: "" # L1-L5
system_layer: "" # meta / domain / delivery
one_liner: "" # ≤30字Step 3:十维评分
按以下 10 个维度逐一评分(1-5 分),每项必须给出一句话理由:
| # | 维度 | 权重 | 检查点 |
| 1 | 清晰度 | 10% | 任务明确?边界清晰?可直接调用? |
| 2 | 可调用性 | 10% | 有明确触发条件?触发规则可判? |
| 3 | 可执行性 | 10% | 有步骤?有判断节点?有异常处理? |
| 4 | 输出稳定性 | 10% | 格式一致?可被下游接力? |
| 5 | 结果质量 | 15% | 有洞察?可执行?有判断? |
| 6 | 复用性 | 10% | 跨项目?跨行业? |
| 7 | 组合性 | 10% | 能与其他 Skill 联动?有前后关系? |
| 8 | 可评估性 | 5% | 有量化标准?有评估规则? |
| 9 | 安全性 | 10% | 有风险清单?有审核机制? |
| 10 | 商业价值 | 10% | 高频?可变现?强差异化? |
Step 4:计算总分
总分 = Σ(各维度得分 × 权重) × 10满分 50 分。
Step 5:分级
| 总分区间 | 等级 | 含义 |
| 45-50 | S 核心资产 | 可产品化、商业化 |
| 35-44 | A 可用 | 可在项目中使用 |
| 25-34 | B 实验 | 可内部测试 |
| 15-24 | C 概念 | 需要重构 |
| <15 | D 无效 | 降级为 Knowledge 或 Prompt |
Step 6:输出评估报告
📋 Skill 评估报告(SMS v1.0 · 十维雷达)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
🏷️ Skill:[name] v[version]
📂 Agent:[parent_agent] | 类型:[type_primary] | 成熟度:[maturity] | 系统层:[system_layer]
📊 十维评分:
1. 清晰度 ★★★★☆ X/5 — [理由]
2. 可调用性 ★★★☆☆ X/5 — [理由]
3. 可执行性 ★★★★★ X/5 — [理由]
4. 输出稳定性 ★★★★☆ X/5 — [理由]
5. 结果质量 ★★★★★ X/5 — [理由]
6. 复用性 ★★★☆☆ X/5 — [理由]
7. 组合性 ★★★★☆ X/5 — [理由]
8. 可评估性 ★★★☆☆ X/5 — [理由]
9. 安全性 ★★★★☆ X/5 — [理由]
10. 商业价值 ★★★★★ X/5 — [理由]
🎯 总分:XX/50
🏆 等级:[S/A/B/C/D] 级
✅ 核心优点:
1. [具体优点]
2. [具体优点]
⚠️ 改进空间:
1. [具体问题 + 改进方向]
2. [具体问题 + 改进方向]
💡 建议:[推荐使用 / 建议优化后使用 / 不推荐]Step 7:更新 registry
将评分结果写入 memory/skill-registry.json 对应 Skill 的 scores、grade、maturity、type_primary 字段。
Spawn 模板
范德调度小能审计技能时的标准命令:
用skill-audit评估{skill-name}的质量批量审计:
用skill-audit审计小能的全部6个子技能安全边界
| 规则 | 说明 |
| 只读不改 | 审计只读取SKILL.md,不修改被审计的技能文件 |
| 结果写自己目录 | 评估报告只写入小能自己的memory/,不写别人的目录 |
| 不删除 | 审计结果不自动触发删除操作,降级建议需人工确认 |
| 安全性必检 | 涉及外部发送、财务、法律的Skill必须标注风险 |
注意事项
- 每项评分必须附理由,不给模糊评价
- 对 L1-L2 的新 Skill 适当宽松,重点看潜力
- 对 L4-L5 的生产级 Skill 严格按标准评
- 安全性为必检项——涉及外部发送、财务、法律的 Skill 必须标注风险
- 跨 Agent 组合性在多 Agent 架构中特别重要,重点评估
- 审计完成后自动通知范德(通过记忆文件或直接回复)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

