which-skill
Skill1 starsChanged 30 days agoMITView on GitHub
问这个场景该用哪个 skill。本仓库 skills 的路由器:任务生命周期主链、自动触发的纪律层、独立工具三类。
12 other projects use a version of this.
Adopted by
Most recently taken up by
- paureis/pau-skillstheir own version, first seen Nov 8, 2026
- leek/agent-skillstheir own version, first seen Nov 2, 2026
- aayushchugh/skillstheir own version, first seen Nov 1, 2026
- TanKaizokuO/claude-skillstheir own version, first seen Oct 20, 2026
- karina-yjm/which-skilltheir own version, first seen Oct 11, 2026
- mik2win/foureyestheir own version, first seen Oct 8, 2026
Used with
Projects with it also use resolving-merge-conflicts, to-issues and 7 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.
GoogleSkillresolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Also in 3 projects that use this
GoogleSkillto-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
Also in 3 projects that use this
Google CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 4 projects that use this
- +6 more from google
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- evist0/okf-matt-skills★ 13same name
- officialunofficial/skills★ 7same name
- leek/agent-skills★ 5same name
- aayushchugh/skills★ 4same name
- icetomoyo/CodingSkills★ 4same name
- dhanji4U/skills★ 2same name
- mik2win/foureyes★ 2same name
- paureis/pau-skills★ 2same name
- risadams/ink-and-agency★ 2same name
- karina-yjm/which-skill★ 1same name
2 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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agentdocs-setupSkill
- agent-docsSkill
- codebase-designSkill
- code-reviewSkill
- commit-msgSkill
- diagnoseSkill
- engramSkill
- handoffSkill
- improve-archSkill
- interviewSkill
- prototypeSkill
- prSkill
- questionnaireSkill
- researchSkill
- review-frontend-productionSkill
- run-ticketSkill
- setup-gatesSkill
- sync-claude-mdSkill
- sync-readmeSkill
- task-retroSkill
- task-specSkill
- task-ticketsSkill
- tddSkill
- teachSkill
- team-devSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- writing-for-agentsSkill
The file
Files
用哪个 skill
你不需要记住每个 skill,问就行。
主流程:想法 → 交付
多数工作沿这条路走:
/agentdocs-setup每仓库一次:初始化.agentdocs/工作区;/interview对齐想法:按设计树无情访谈,术语与决策当场沉淀。开始任何有分量的变更前先到这里;- 分支:这个任务一个会话装得下吗?
- 装不下 →
/wayfinder(见"超大会话工程"); - 装得下 →
/task-spec把当前对话定稿为任务规格;
- 装不下 →
- 需要拆分执行 →
/task-tickets拆为带阻塞边的工单; - 执行,二选一:
/run-ticket逐张轻量执行(每张新会话,或在本会话直接做小任务);/team-dev组队并行(lead 规划协调,teammates 执行); /task-retro收口:状态核对、归档、知识写回、环境改进。
执行内部由纪律层驱动(见下):构建走 tdd(红绿循环,一片一循环),收尾走 code-review(两轴审查,Spec 轴以工单为源)。单独想测试先行或审查某个分支时,直接点名它们。
超大会话工程
/wayfinder:想法大到一次会话想不清楚(全系统重构、新产品线)。它在 .agentdocs/workflow/ 下建决策地图与决策工单,每会话解决一张,雾区随前沿渐进毕业。答案写在工单的 ## 答案,地图只留主旨与链接。工单清空后回到主流程的 /task-spec,不直接执行。
会话边界
/handoff:把当前会话压缩为交接文档(落任务目录),给新会话、新目录或同事。阶段边界上的其他选项:继续、/clear、子代理、/compact——能继续就继续,清空是最后选项。
自动触发的纪律层
不敲命令,模型按场景自己到达。想显式点名时:
- agent-docs:
.agentdocs/项目的文档读写纪律,贯穿所有环节; - tdd:说"测试先行"、"红绿重构";
- code-review:说"审查这个分支/PR/变更";
- research:说"调研一下 X"(后台按一手来源查证并落盘);
- prototype:说"做个原型验证这个状态模型/UI";
- diagnose:报 bug、说"诊断这个";
- pr:写 PR 描述时;
- codebase-design:讨论模块接口、接缝放哪;
- review-frontend-production:说"体检/审查这个前端项目",输出有证据的问题、修复方案与验收条件;
- wait-what:上一条没看懂,一键重讲。
代码库健康
/improve-arch:定期(几天一次)扫描代码库找深化机会(浅模块变深模块),出 HTML 报告,选定一个进入/interview细化;- codebase-design(自动触发)是它底下的设计词汇:深模块、接缝、杠杆、局部性。
方法与工具
- writing-for-agents(自动触发):写 skill、AGENTS.md、任何 agent 文档时的方法论,维护本仓库必读;
/setup-gates:给项目装门禁(pre-commit 检查、危险 git 命令拦截);/wizard:生成向导脚本,带人做只有人能做的操作(配 secrets、走第三方控制台);/questionnaire:卡住你的答案在别人手里时,生成给对方填的问卷;/teach:用当前目录做教学工作区,多会话学一个主题。
独立工具
/commit-msg:生成 Conventional Commits 提交信息;/sync-readme与/sync-claude-md:文档与实际状态对账;/engram:跨项目全局记忆的设置、整理与同步。
上下文卫生
- 对齐 → task-spec → task-tickets 保持同一个不间断的上下文窗口(设计一次成型);
- 每张工单的执行从全新上下文起步,teammate 之间只传工单路径等上下文指针,不复制内容——状态的家在文件系统,不在会话;
- 会话逼近注意力上限时,在最近的阶段边界
/compact,不要带着降级的推理硬推。
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.

