ask-matt
Skill5 starsChanged 3 months agoMITView on GitHub
根据当前情境推荐合适的 skill 或工作流;作为本仓库已收录技能的路由入口。
123 other projects use a version of this.
Adopted by
Most recently taken up by
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- 5thlayer/skillworkstheir own version, first seen Nov 8, 2026
- zhikedan/mattpocock-skills-dshtheir own version, first seen Nov 8, 2026
- op3616windows/skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- miklschmidt/archboardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, claude-handoff and 9 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.
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 30 projects that use this
ryotaroh180105Skillclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Also in 33 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 36 projects that use this
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 5 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 62 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 35 projects that use this
Other versions123 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 123
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- GreyDGL/PentestGPT★ 16ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
- moeru-ai/xsai★ 667same name
- nodetool-ai/nodetool★ 615same name
113 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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- documenting-codeSkill
- implementSkill
- implement-specSkill
- integrating-frontend-apisSkill
- organizing-frontend-componentsSkill
- prototypeSkill
- tddSkill
- writing-vue-componentsSkill
- researchSkill
- teachSkill
- writing-for-agentsSkill
- codebase-designSkill
- domain-modelingSkill
- grill-with-docsSkill
- to-specSkill
- to-ticketsSkill
- code-reviewSkill
- diagnosing-bugsSkill
- improve-codebase-architectureSkill
- retroSkill
- execute-planSkill
- git-commitSkill
- grillingSkill
- grill-meSkill
- handoffSkill
- prSkill
- setup-matt-pocock-skillsSkill
- triageSkill
- usage-disclosureSkill
- wait-whatSkill
- wayfinderSkill
The file
Files
询问 Matt(Ask Matt)
不必记住每个技能,直接询问适合当前情境的流程。
说明某个技能的职责或建议跳过某一步骤之前,先读取该技能的 SKILL.md;这里的摘要仅供定位。
**流程(flow)是一条穿过技能的路径。大多数路径沿主流程(main flow)**前进,**入口支线(on-ramps)**汇入其中。其他技能独立运行,或提供底层词汇。
主流程:想法 → 交付(idea → ship)
/grill-with-docs:通过访谈磨砺想法。在工作目录中从这里开始,将认知保存在GLOSSARY.md和 ADR 中。没有工作目录时使用/grill-me;两者都使用/grilling,前者会留下书面记录。- **需要可运行的答案吗?**如果状态、业务逻辑或 UI 无法仅靠对话确定,就绕道
/prototype。原型位于独立目录,使用/handoff导出上下文,在新会话中构建原型,再把获得的认知交接回原始想法会话。 这是跨会话的构建吗?
- 是:使用
/to-spec综合规格,再用/to-tickets按用户选择的场景拆分或曳光弹工单(tracer-bullet tickets)模式组织工单,声明阻塞边(blocking edges);尚未选择时由该技能询问。随后选择一种实施方式:- 每个工单使用一次
/implement,工单之间使用/clear清空上下文。本地跟踪器在.scratch/<feature>/issues/中逐工单存放文件,按阻塞项优先顺序处理;真实跟踪器使用原生阻塞关系,任何阻塞项已完成的工单都可领取。每个工单自足,前一个工单的上下文可以丢弃。 - 使用
/implement-spec一次实施整份规格。它把工单视为任务图(task graph),在可领取前沿(frontier)并行运行实施子代理,最终汇入一条集成分支(integration branch)。适用于希望编排整次构建的情况。
- 每个工单使用一次
- 否:在当前上下文中直接使用
/implement。
两种方式都使用
/tdd,一次完成一个红绿切片,并以/code-review沿 Standards + Spec 两轴收尾。/implement每项工作都测试和审查;/implement-spec的各实施代理使用 TDD,最后统一审查集成分支。只有具体行为需要测试优先开发时,可单独使用/tdd;需要依据固定点审查分支或 PR 时,可单独使用/code-review。创建 PR 时使用
/pr编写正文:最小图示、前后证据,以及单向门或双向门判断。它允许模型隐式调用。- 是:使用
/retro:构建后复盘会话,尤其适用于遇到波折的构建。它提出改进智能体环境的建议:导航指针、自动检查、审查规范、引导文件和工具。机械性错误转为确定性检查,判断性事项转为编码规范,让后续构建获得更好的环境。
上下文卫生(Context hygiene)
将追问、规格和工单保持在一个不中断的上下文窗口中:完成 /to-tickets 前不要压缩或清空,使它们建立在同一套推理上。随后每个 /implement 从新上下文开始,以工单为依据。清空前在被复盘的会话中运行 /retro;已经清空时,向它提供该会话日志。
限制来自智能区(smart zone)。上游以先进模型约 150k tokens 作为参考;实际应结合模型与当前上下文判断。若在 /to-tickets 前接近有效窗口上限,在最近的阶段边界使用 /compact 后继续,按下文的阶段边界决策树选择。
入口支线(On-ramps)
- 缺陷和外部请求堆积 →
/triage。议题经过分诊角色,形成智能体可领取的简报,供/implement实施。只分诊未经处理的外部输入;/to-tickets生成的工单已经准备好实施。 - 有东西坏了 →
/diagnosing-bugs。用于棘手缺陷、间歇性失败或两个已知正确状态之间的回退。先建立已经能在当前缺陷上变红的紧密反馈循环(tight feedback loop),再用回归测试修复。修复后在同一会话运行/retro,评估如何预防;若问题是缺少可锁定行为的接缝,再考虑/improve-codebase-architecture。 - 大型、充满未知的工作 →
/wayfinder。将未决问题绘成由决策工单(decision tickets)组成的共享地图(shared map),逐项解决直到路线清晰。它投入较高,适用于单次会话无法掌握的想法;范围已经明确的功能从主流程开始。地图清晰后交接给/to-spec,将链接中的决策综合成可构建计划,再拆工单并实施。只有工作最终足够小时才直接进入/implement。
代码库健康(Codebase health)
/improve-codebase-architecture:寻找深化机会(deepening opportunities),按用户方向或近期改动确定范围。选中候选项后,可在/grill-with-docs处进入主流程;/codebase-design提供设计候选项的词汇。
底层词汇(Vocabulary underneath)
/domain-modeling:磨砺领域语言,澄清模糊或多义术语,将难以逆转的决策记录为 ADR,维护GLOSSARY.md。/codebase-design:设计深模块(deep modules)的形态,使用 module、interface、depth、seam、adapter、leverage、locality,在清晰接缝上的小接口后放置大量行为。/tdd与架构评估都使用它。
阶段边界(Phase boundaries)
阶段是一块完整工作,例如追问、实现、QA。在两个阶段之间按顺序选择:
- 继续(Continue):下一阶段需要完整推理,或当前窗口足够时,留在当前会话。
/clear:当前上下文与下一阶段完全无关时清空。/handoff:更换执行工具、目录、同事,或在阶段中途分出支线时,写出可移植文件。- 子代理(Subagent):范围明确且无需实时引导的任务,交给独立窗口执行并返回报告。
/compact:前面都不适用时,压缩相关上下文,保留下一阶段需要的信息。
阅读 PHASE-BOUNDARIES.md 获取完整决策树。只在阶段边界作选择;阶段中途继续,或将可独立执行的剩余工作分给子代理。
独立技能(Standalone)
/grill-me:没有工作目录时的无状态访谈,不保存本地内容;在工作目录中优先使用留下记录的/grill-with-docs。/grilling:访谈原语,按轮次处理当前问题前沿。事实由智能体查清,决策由用户作出。多个流程在内部使用它,也可直接使用。/prototype:用一次性代码回答一个设计问题。将验证的决策吸收到真实代码,并把原型保存在 main 之外的prototype/<name>分支上,作为一手来源(primary source),从实现议题中链接。/research:由后台智能体(background agent)调查一手来源(primary sources),生成带引用的仓库 Markdown 文件;调研材料可带入/grill-with-docs。/wait-what:上一条解释没有讲清楚时,补充背景,用简明语言和GLOSSARY.md中的领域词汇重新说明,可在任意流程中使用。/teach:以当前目录作为有状态工作区,跨会话学习概念。/writing-for-agents:编写和编辑智能体会阅读的技能、AGENTS.md 与指针文档。
本仓库另有前端组件组织、Vue 实现、API 对接、注释维护、/git-commit 和 /usage-disclosure 等本地技能,按其描述选择。/git-commit 使用 Conventional Commits;/usage-disclosure 说明回复实际使用的技能。
前置条件(Precondition)
首次运行工程流程前,用户运行 /setup-matt-pocock-skills,配置议题跟踪器、分诊标签和文档布局,也可指定自定义跟踪器。
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.

