工程技能集(改编自 mattpocock/skills)
下载地址
https://www.zhengdianxue.com/wp-content/uploads/skills/user_c01c51ce--mattpocock-skills-zh.zip将提示词发送给你的 AI 安装该 skills
请根据 https://skillhub.cn/install/skillhub.md,安装 @user_c01c51ce/mattpocock-skills-zh。面向真实软件工程的 AI 技能合集,改编自 mattpocock/skills(MIT,作者 Matt Pocock),已移植为 WorkBuddy/CodeBuddy 兼容格式并全量汉化注释。收录 36 个技能,覆盖:需求拷问对齐(grilling / grill-me)、测试驱动开发(tdd)、难 bug 诊断(diagnosing-bugs)、双轴代码审查(code-review)、深模块设计词汇(codebase-design)、领域建模与 ADR(domain-modeling)、规格与工单拆分(to-spec / to-tickets)、实施(implement / implement-spec)、issue 分诊(triage)、超大任务寻路(wayfinder)、一次性原型(prototype)、一手来源调研(research)、架构改进(improve-codebase-architecture)、PR 正文规范(pr)、交互式向导(wizard)、会话交接(handoff)、多会话教学(teach)、为 agent 写文档(writing-for-agents)等。
触发场景:用户要开工前对齐需求、写测试优先、排查疑难 bug、做代码审查、设计模块接口、拆解大型任务、写 PR、做技术调研、沉淀领域词汇表,或询问「有哪些工程技能可用 / 该用哪个流程」时。另附 1 篇原创经验笔记(分布式唯一 ID 选型,见 experience/),该篇为原创内容,与上游项目无关。免费使用。
阅读全文 (展开查看完整说明)
概述
36 个面向真实软件工程的技能,供 agent 在任务中按需加载。本技能集免费使用。
来源与许可(务必知悉)
- 原作者:Matt Pocock | 原始仓库:https://github.com/mattpocock/skills
- 许可:MIT License,Copyright (c) 2026 Matt Pocock(全文见包内
LICENSE.md) - 本包性质:非原创。本包是对上述开源项目的移植改编,已做 5 处非语义适配(frontmatter 规范化、剥离 Codex 专有元数据、斜杠命令语法替换、注入中文移植说明、补充 WorkBuddy/CodeBuddy 使用指引)。
技能正文经逐字节校验与原版 100% 一致,改动仅限格式与调用语法。详见包内 ATTRIBUTION.md。
- 未收录:上游 2 个技能因硬依赖 Claude Code 运行时未移植(
claude-handoff依赖claude --bg;git-guardrails-claude-code依赖 Claude Code hooks)。
如何使用
- 先读这个索引判断哪个技能匹配当前任务(下表)。
- 再读对应技能的完整正文:
references/<分类>/<技能名>/SKILL.md,并遵循其全部指令与纪律。 - 技能正文中若引用同目录下的辅助文件(如
LOGIC.md、templates/*.sh、*-FORMAT.md),一并读取后再执行。 - 技能之间存在调用关系(如
implement会调用tdd与code-review):按正文要求,改为读取对应技能的 SKILL.md 并执行其纪律。
关键纪律:不要凭本索引的摘要代替技能正文执行。 索引只用于选路,正文才是权威。
能力索引
工程类(日常代码工作) | references/engineering/
| 技能 | 路径 | 用途 |
|---|---|---|
ask-matt | references/engineering/ask-matt/SKILL.md | Ask which skill or flow fits your situation. A router over the skills in this repo. |
code-review | references/engineering/code-review/SKILL.md | Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". |
codebase-design | references/engineering/codebase-design/SKILL.md | Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. |
diagnosing-bugs | references/engineering/diagnosing-bugs/SKILL.md | Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. |
domain-modeling | references/engineering/domain-modeling/SKILL.md | Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR. |
grill-with-docs | references/engineering/grill-with-docs/SKILL.md | A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. |
implement | references/engineering/implement/SKILL.md | Implement a piece of work based on a spec or set of tickets. |
implement-spec | references/engineering/implement-spec/SKILL.md | Implement the result of /to-spec and /to-tickets in code. |
improve-codebase-architecture | references/engineering/improve-codebase-architecture/SKILL.md | Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. |
pr | references/engineering/pr/SKILL.md | Use when writing a PR body. |
prototype | references/engineering/prototype/SKILL.md | Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like. |
research | references/engineering/research/SKILL.md | Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent. |
retro | references/engineering/retro/SKILL.md | Conduct a retrospective on a coding session. |
setup-matt-pocock-skills | references/engineering/setup-matt-pocock-skills/SKILL.md | Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills. |
tdd | references/engineering/tdd/SKILL.md | Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. |
to-spec | references/engineering/to-spec/SKILL.md | Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed. |
to-tickets | references/engineering/to-tickets/SKILL.md | Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker). |
triage | references/engineering/triage/SKILL.md | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. |
wayfinder | references/engineering/wayfinder/SKILL.md | Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear. |
wizard | references/engineering/wizard/SKILL.md | Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself. |
通用工作流(不限于代码) | references/productivity/
| 技能 | 路径 | 用途 |
|---|---|---|
grill-me | references/productivity/grill-me/SKILL.md | A relentless interview to sharpen a plan or design. |
grilling | references/productivity/grilling/SKILL.md | Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases. |
handoff | references/productivity/handoff/SKILL.md | Compact the current conversation into a handoff document for another agent to pick up. |
teach | references/productivity/teach/SKILL.md | Teach the user a new skill or concept, within this workspace. |
to-questionnaire | references/productivity/to-questionnaire/SKILL.md | Turn a decision you can't fully answer into a questionnaire for someone else to fill in. |
wait-what | references/productivity/wait-what/SKILL.md | Stop. That last message did not land: re-pitch it. |
writing-for-agents | references/productivity/writing-for-agents/SKILL.md | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. |
实验区(上游未打磨,谨慎使用) | references/in-progress/
| 技能 | 路径 | 用途 |
|---|---|---|
chief-of-staff | references/in-progress/chief-of-staff/SKILL.md | Pursue a long-running goal in a single session by co-ordinating subagents. |
loop-me | references/in-progress/loop-me/SKILL.md | Grill me about specs for the workflows I want to build, within this workspace. |
setup-ts-deep-modules | references/in-progress/setup-ts-deep-modules/SKILL.md | Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. User-invoked. |
writing-beats | references/in-progress/writing-beats/SKILL.md | Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it. |
writing-fragments | references/in-progress/writing-fragments/SKILL.md | Writing, explore: mine raw fragments, no structure yet. |
writing-shape | references/in-progress/writing-shape/SKILL.md | Writing, exploit: shape raw material into an article, paragraph by paragraph. |
特定场景 | references/misc/
| 技能 | 路径 | 用途 |
|---|---|---|
migrate-to-shoehorn | references/misc/migrate-to-shoehorn/SKILL.md | Migrate test files from as type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace as in tests, or needs partial test data. |
scaffold-exercises | references/misc/scaffold-exercises/SKILL.md | Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section. |
setup-pre-commit | references/misc/setup-pre-commit/SKILL.md | Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing. |
典型工作流
- 想法 → 上线主链路:grill-with-docs(拷问对齐)→ to-spec(成文)→ to-tickets(拆工单)→ implement / implement-spec(实施,内含 tdd)→ code-review(双轴审查)→ pr(提 PR)
- 困难 bug:diagnosing-bugs(复现→最小化→假设→插桩→修复→回归)
- 架构治理:improve-codebase-architecture(扫描深化机会,出 HTML 报告)→ codebase-design(深模块词汇)→ domain-modeling(沉淀词汇表与 ADR)
- 巨型任务:wayfinder(决策工单地图,逐个解决)
- 通用:grill-me(拷问)/ handoff(会话交接)/ research(一手来源调研)/ teach(多会话教学)
附:经验笔记(原创,与上游无关)
experience/distributed-unique-id.md — 分布式唯一 ID 的选择与落地经验:五种方案的真实边界与量化对照、UUIDv7 这个常被漏掉的选项、Snowflake 的 epoch 到期与时钟回拨分级处理、容器环境下 worker id 分配的实际取舍、号段 step 的估算公式,以及由四个真实事故反推的检查清单。
触发场景:用户在设计主键、纠结自增 / UUID / Snowflake / 号段、排查 ID 重复或时钟回拨,或在准备「如何为数十亿用户生成唯一 ID」这类系统设计面试时,读这一篇。
免责:本节及该文件为原创内容,不属于 mattpocock/skills 项目,不受上游 MIT 许可约束(本包整体仍可免费使用)。其余
references/下全部技能均来自上游。