record-decision
Skill2 starsChanged 7 months agoMITView on GitHub
将当前任务中做出的非显而易见技术决策写入 docs/decisions/,供 AI 和团队在后续接触相关代码时参考
11 other projects use a version of this.
Adopted by
Most recently taken up by
- jabbott-iii/Tidepooltheir own version, first seen Nov 8, 2026
- Walsworth-Group/physkittheir own version, first seen Nov 8, 2026
- Memolok/Claude-plugintheir own version, first seen Nov 6, 2026
- rpraharaj/ai-sdlctheir own version, first seen Nov 1, 2026
- rpraharaj/ai-engineertheir own version, first seen Nov 1, 2026
- shioki/Cursor-Knowledge-Management-Systemtheir own version, first seen Oct 9, 2026
Used with
Projects with it also use verify and handoff.
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.
Microsoft AzureSkillverify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- hardness1020/VibeFlow★ 8same name
- Walsworth-Group/physkit★ 7same name
- iopsystems/skills-mcp★ 6same name
- YangFan-Code-Star/context-dev★ 2same name
- jabbott-iii/Tidepool★ 1same name
- Memolok/Claude-plugin★ 1same name
- rpraharaj/ai-engineer★ 1same name
- shioki/Cursor-Knowledge-Management-System★ 1same name
- deanmikan/ai-native-company-starter★ 0same name
- Luis85/agentic-workflow★ 0same name
1 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 repository26 other files it gives its agents.
- advise-tech-stackSkill
- commit-with-affectsSkill
- db-dev-guideSkill
- export-db-indexesSkill
- frontend-dev-guideSkill
- frontend-ux-evaluatorSkill
- generate-pr-descriptionSkill
- generate-test-from-impactSkill
- generate-test-skeletonSkill
- lock-global-conventionsSkill
- plan-component-hierarchySkill
- plan-page-mapSkill
- proposal-reviewSkill
- propose-workflow-improvementsSkill
- pr-self-reviewSkill
- review-guardrailsSkill
- run-pending-specsSkill
- run-testsSkill
- scan-bundle-bloatSkill
- scan-code-hygieneSkill
- scan-dead-routesSkill
- scan-frontend-qualitySkill
- scan-orphan-componentsSkill
- scan-unused-exportsSkill
- sync-llm-contextSkill
- verify-specSkill
The file
Files
Record Decision Skill
单独调用:
/record-decision 认证方案在工作流中调用:当 auto-dev / dev-flow 在完成一个任务时,AI 检测到本次开发中存在非显而易见的决策,自动提议触发
触发判断条件
AI 在任务结束时,检查是否满足以下任意一条,满足则提议写决策记录:
- 本次选择了一个有明显替代方案的技术路线(选 A 而不选 B)
- 某个模块加了"不能随意改动"的约束(如权限检查、事务边界)
- 故意绕开了通用模式(如某接口不走统一的错误处理中间件)
- 依赖了一个会消失的外部约束(如"目前移动端不支持 Cookie")
- 用户在任务过程中说了"这里要注意"、"不要改这里"之类的话
不需要写决策记录的情况:
- 行业通用最佳实践(用索引、写单元测试等)
- 明显的权宜之计(临时 hack,已在代码注释里标注)
- 纯偏好选择(没有约束意义)
执行步骤
Step 1:从上下文提取决策要素
从当前对话和代码中提取:
- 面临的背景/约束是什么
- 做了什么决定(一句话)
- 为什么(关键驱动因素)
- 选择带来了哪些代价
- 哪些改动会破坏这个决策(禁止事项)
- 涉及哪些代码路径(affects 字段)
Step 2:生成决策文件
按 docs/decisions/_template.md 格式写入 docs/decisions/{{topic-slug}}.md。
文件名规则:全小写,空格用连字符,如 jwt-auth-strategy.md、pagination-cursor-vs-offset.md。
必须在 frontmatter 结束后立即生成 QUICK 摘要行(供 Phase 0 低成本读取):
<!-- QUICK: NEVER [禁止事项1,≤15字] | NEVER [禁止事项2,≤15字] -->规则:
- 只写禁止事项,不写原因(原因在正文)
- 每条 ≤ 15 字
- 最多 3 条,用
|分隔 - 这是 AI 每次任务的低成本入口,必须高度精炼
Step 3:更新 README.md 索引
在 docs/decisions/README.md 的索引表中追加一行:
| [决策标题](文件名.md) | src/api/auth/, backend/app/ | NEVER 把 JWT 换成 Session Cookie |Step 4:输出确认
[DECISION RECORDED] docs/decisions/jwt-auth-strategy.md
核心约束已登记:
- NEVER 把 access token TTL 调长超过 2 小时
- NEVER 把 access token 存入 localStorage
下次 AI 接触 backend/app/routers/auth/ 时会先读取此决策。约束
- MUST 写入
docs/decisions/目录,不写在其他位置 - MUST 更新
README.md索引,否则 AI 路由无法生效 - NEVER 把显而易见的常识写进来(浪费 token,稀释真正重要的决策)
- NEVER 修改
.agents/rules/中的内容(知识库写保护)——决策记录属于docs/,不属于规则层 - 决策文件由 AI 起草,必须经人工确认后写入(遵从 core.md 知识库写入权限红线的精神)
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.

