report-format
Skill2 starsChanged 6 months agoMITView on GitHub
尚书省 report 模式回奏格式规范,定义回奏必备字段与结构
4 other projects use a version of this.
Adopted by
Most recently taken up by
- lklimek/claudiustheir own version, first seen Nov 5, 2026
- ku5ic/claude-kittheir own version, first seen Nov 4, 2026
- palmeheskd/claude-skillstheir own version, first seen Oct 25, 2026
- PitShalom/iaops-k8stheir own version, first seen Oct 13, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- ku5ic/claude-kit★ 2same name
- lklimek/claudius★ 1same name
- palmeheskd/claude-skills★ 0same name
- PitShalom/iaops-k8s★ 0same name
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 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
- kejuSkill
- morning-courtSkill
- parallel-executionSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- token-optimizationSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
Skill: 回奏格式
适用 Agent:尚书省 加载时机:尚书省 report 模式(汇总完毕准备回奏时)
回奏报告格式
{
"report": {
"plan_id": "PLAN-20260312-001",
"title": "用户登录模块开发",
"status": "delivered",
"summary": "简要执行结果描述",
"subtask_results": [
{
"task_id": "TASK-001",
"department": "gongbu",
"status": "done",
"output": "src/auth/login.ts"
},
{
"task_id": "TASK-002",
"department": "xingbu",
"status": "done",
"output": "tests/auth/login.test.ts"
}
],
"criteria_verification": [
{ "criterion": "JWT Token 正确签发", "result": "pass", "evidence": "src/auth/login.ts:42 签发逻辑 + 单测通过" },
{ "criterion": "单元测试覆盖率 > 80%", "result": "pass", "evidence": "coverage 报告 87%" }
],
"issues": [],
"recommendations": ""
}
}回奏流程
尚书省编写回奏报告后,通过 SendMessage 发送至太子(Lead),由太子汇总呈报皇上。太子不得修改回奏内容,仅负责中转与格式化呈报。
必备字段
plan_id:关联的方案编号status:delivered / partial / failed / rejectedsummary:一段话概括执行结果subtask_results:每个子任务的完成状态与产出物issues:执行过程中遇到的问题(即使已解决也需记录)
闭环验收(status=delivered 强制)
status 标记为 delivered 时,必须附 criteria_verification[] 逐条验收原草案的 acceptance_criteria,且:
- 数组非空,每条含
criterion/result/evidence - 每条
result必须为pass(存在fail则不得标记 delivered) - 每条
evidence须非空,给出可核验的取证(文件路径、测试结果、覆盖率数据等)
此为运行时律令:H08 message-gateway 经 validate-payload.sh 强制校验,不满足则封驳。partial / failed / rejected 状态不要求闭环验收,但应在 issues / summary 中说明缺口。
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.

