Skills directory
Publicly available Agent skills, tracked and ranked by skill-sets.md, rated by you, and agents! Search by name or narrow to a topic.
| Rank | Skill | Installs | Recent (7d) | Create set |
|---|---|---|---|---|
| 2 | A relentless interview to sharpen a plan or design. | 1.4m+ | +30k+<5% | Add |
| 6 | A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go. | 1.2m+ | +30k+<5% | Add |
| 8 | Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. Agent operations | 1.2m+ | +30k+<5% | Add |
| 10 | Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. Testing | 1.1m+ | +30k+<5% | Add |
| 12 | 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. | 1m+ | +30k+<5% | Add |
| 13 | Compact the current conversation into a handoff document for another agent to pick up. | 1m+ | +20k+<5% | Add |
| 15 | 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. | 1m+ | +30k+<5% | Add |
| 16 | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. Agent operationsProject management | 1m+ | +20k+<5% | Add |
| 17 | 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. Code authoring | 1m+ | +20k+<5% | Add |
| 20 | 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. | 910k+ | +30k+<5% | Add |
| 22 | Teach the user a new skill or concept, within this workspace. | 890k+ | +20k+<5% | Add |
| 23 | 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 th | 890k+ | +30k+<5% | Add |
| 24 | Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow. | 870k+ | +20k+<5% | Add |
| 48 | 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?). Agent operationsCode review | 830k+ | +30k+<5% | Add |
| 51 | Implement a piece of work based on a spec or set of tickets. Code authoring | 810k+ | +20k+<5% | Add |
| 53 | Ask which skill or flow fits your situation. A router over the skills in this repo. | 800k+ | +20k+<5% | Add |
| 60 | 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. Project management | 750k+ | +20k+<5% | Add |
| 62 | 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. | 750k+ | +20k+<5% | Add |
| 63 | 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. Research and search | 750k+ | +20k+<5% | Add |
| 64 | 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 tr | 740k+ | +20k+<5% | Add |
| 76 | 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 migrat | 580k+ | +20k+<5% | Add |
| 95 | Turn a decision you can't fully answer into a questionnaire for someone else to fill in. | 530k+ | +20k+<5% | Add |
| 97 | Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Co | 520k+ | +10k+<5% | Add |
| 100 | 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. | 510k+ | +10k+<5% | Add |
| 102 | Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it. | 500k+ | +10k+<5% | Add |
| 103 | Writing, exploit: shape raw material into an article, paragraph by paragraph. | 500k+ | +10k+<5% | Add |
| 104 | Writing, explore: mine raw fragments, no structure yet. | 500k+ | +10k+<5% | Add |
| 105 | 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. | 500k+ | +10k+<5% | Add |
| 106 | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. Documentation | 500k+ | +20k+5% | Add |
| 107 | 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. Code authoringTesting | 500k+ | +10k+<5% | Add |
| 113 | Stop. That last message did not land: re-pitch it. | 480k+ | +20k+5% | Add |
| 135 | Grill me about specs for the workflows I want to build, within this workspace. | 460k+ | +10k+<5% | Add |
| 141 | Hand the current conversation off to a fresh background agent that picks up the work immediately. Agent operations | 440k+ | +10k+<5% | Add |
| 262 | 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. | 180k+ | +10k+<5% | Add |
| 562 | Implement the result of /to-spec and /to-tickets in code. | 50k+ | +20k+5% | Add |
| 605 | Conduct a retrospective on a coding session. | 50k+ | +20k+5% | Add |
| 945 | Pursue a long-running goal in a single session by co-ordinating subagents. | 20k+ | +10k+10% | Add |
| 2586 | grill-mevinvcn/mattpocock-skills-zh-cn/grill-me 一个用来打磨计划或设计的持续追问式访谈。 | 3k+ | +100+<5% | Add |
| 2622 | Use when writing a PR body. | 3k+ | +20k+10% | Add |
| 2694 | grill-with-docsvinvcn/mattpocock-skills-zh-cn/grill-with-docs 一个用来打磨计划或设计的持续追问式访谈,并在过程中创建文档(ADRs 和词汇表)。 Documentation | 3k+ | +30+<5% | Add |
| 2801 | setup-matt-pocock-skillsvinvcn/mattpocock-skills-zh-cn/setup-matt-pocock-skills 为此仓库配置 engineering skills:设置其 issue tracker、triage labels 词汇与 domain docs 布局。在首次使用其他 engineering skills 前运行一次。 | 3k+ | +30+<5% | Add |
| 2829 | handoffvinvcn/mattpocock-skills-zh-cn/handoff 把当前对话压缩成交接文档,让另一个代理接手。 | 3k+ | +100+<5% | Add |
| 2830 | tddvinvcn/mattpocock-skills-zh-cn/tdd 测试驱动开发。适用于用户想用先写测试的方式构建功能或修复缺陷、提到 “red-green-refactor”,或需要集成测试时。 Testing | 3k+ | +30+<5% | Add |
| 2844 | improve-codebase-architecturevinvcn/mattpocock-skills-zh-cn/improve-codebase-architecture 扫描代码库中的深化机会,生成可视化 HTML 报告,然后围绕你选中的候选项继续追问。 | 3k+ | +30+<5% | Add |
| 2879 | prototypevinvcn/mattpocock-skills-zh-cn/prototype 构建一次性原型来回答一个设计问题。适用于用户想验证某个 state model 或 logic 是否感觉对,或探索 UI 应该长什么样时。 Code authoring | 3k+ | +30+<5% | Add |
| 2935 | triagevinvcn/mattpocock-skills-zh-cn/triage 让 issues 和 external PRs 通过一组 triage roles 状态机,分类、验证、必要时 grilling,并写出 agent-ready briefs。 | 3k+ | +30+<5% | Add |
| 2989 | git-guardrails-claude-codevinvcn/mattpocock-skills-zh-cn/git-guardrails-claude-code 设置 Claude Code hooks,在危险 git commands(push、reset --hard、clean、branch -D 等)执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks,或在 Claude Code 中阻止 git push/reset 时。 | 3k+ | +30+<5% | Add |
| 2992 | scaffold-exercisesvinvcn/mattpocock-skills-zh-cn/scaffold-exercises 创建包含章节、题目、答案和讲解的练习目录结构,并确保通过 linting。适用于用户想 scaffold exercises、创建 exercise stubs,或设置新的课程章节时。 | 3k+ | +30+<5% | Add |
| 2996 | setup-pre-commitvinvcn/mattpocock-skills-zh-cn/setup-pre-commit 在当前仓库设置 Husky pre-commit hooks,集成 lint-staged (Prettier)、类型检查和测试。适用于用户想添加 pre-commit hooks、设置 Husky、配置 lint-staged,或在提交时运行格式化、类型检查和测试时。 | 3k+ | +30+<5% | Add |
| 3019 | migrate-to-shoehornvinvcn/mattpocock-skills-zh-cn/migrate-to-shoehorn 将测试文件从 `as` 类型断言迁移到 @total-typescript/shoehorn。适用于用户提到 shoehorn、想替换测试中的 `as`,或需要局部测试数据时。 Testing | 3k+ | +30+<5% | Add |