Skills directory

A relentless interview to sharpen a plan or design.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

1 copy from other publishers not shown

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

1 copy from other publishers not shown

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.

Compact the current conversation into a handoff document for another agent to pick up.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

Teach the user a new skill or concept, within this workspace.

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

1 copy from other publishers not shown

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

1 copy from other publishers not shown

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?).

1 copy from other publishers not shown

Implement a piece of work based on a spec or set of tickets.

1 copy from other publishers not shown

Ask which skill or flow fits your situation. A router over the skills in this repo.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

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.

1 copy from other publishers not shown

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

1 copy from other publishers not shown

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

1 copy from other publishers not shown

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

1 copy from other publishers not shown

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

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.

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Writing, explore: mine raw fragments, no structure yet.

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.

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

1 copy from other publishers not shown

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.

Stop. That last message did not land: re-pitch it.

1 copy from other publishers not shown

Grill me about specs for the workflows I want to build, within this workspace.

Hand the current conversation off to a fresh background agent that picks up the work immediately.

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.

Implement the result of /to-spec and /to-tickets in code.

Conduct a retrospective on a coding session.

Pursue a long-running goal in a single session by co-ordinating subagents.

一个用来打磨计划或设计的持续追问式访谈。

Use when writing a PR body.

1 copy from other publishers not shown

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）。

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。

把当前对话压缩成交接文档，让另一个代理接手。

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。

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。

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。

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。

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。

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。

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。

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。