keju
Skill2 starsChanged 6 months agoMITView on GitHub
系统一致性验证——检查 Skill frontmatter、Hook 语法、governance-core 与 team-bootstrap 角色一致性、受保护文件同步
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-frameworkSkill
- architecture-overviewSkill
- audit-boundariesSkill
- biannianSkill
- communication-protocolsSkill
- dispatch-rulesSkill
- fault-toleranceSkill
- governance-coreSkill
- hanlinSkill
- intent-classificationSkill
- morning-courtSkill
- parallel-executionSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- report-formatSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- token-optimizationSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
Skill: 科举
适用 Agent:太子(Lead) 加载时机:皇上输入
/keju时,或系统自检时
功能
全面验证三省六部系统的内部一致性,发现配置偏差与潜在问题。类似 lint + integration test。
检查项目
四类检查:Skill frontmatter 格式、Hook 脚本语法、角色名/agent_id 一致性、受保护文件列表同步。
📎 详细规则见
keju-checklist.md
输出格式
📋 科举成绩单
考试日期:2026-03-13
一、Skill Frontmatter(x/y 通过)
✅ morning-court — 通过
❌ xxx — ERROR: 缺少 description 字段
二、Hook 脚本(x/y 通过)
✅ H01-governance-shield.sh — 通过
⚠️ H03-audit-logger.sh — WARN: 缺少可执行权限
三、角色一致性(通过/未通过)
✅ 所有来源一致
或
❌ roles-liubu.md 中缺少 agent_id: libu_hr
四、受保护文件同步(通过/未通过)
✅ 核心文件均在保护列表中
或
⚠️ H06 未包含 CLAUDE.md
总评:x ERROR / y WARN / z INFO
状元 🏆 / 进士 / 举人 / 落榜评级规则:
- 0 ERROR + 0 WARN = 状元
- 0 ERROR + ≤3 WARN = 进士
- 0 ERROR + >3 WARN = 举人
- ≥1 ERROR = 落榜
约束
- 检查过程为只读操作,不修改任何文件
- 发现 ERROR 时建议修复方案但不自动修复
- 成绩单必须呈报皇上,不得隐瞒不通过项
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.

