repo-writing
Applies Robota's repository writing rules for `.design/`, general documentation, and conventional commit messages. Use when editing docs, ADRs, design notes, or preparing commit text.
Best use case
repo-writing is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Applies Robota's repository writing rules for `.design/`, general documentation, and conventional commit messages. Use when editing docs, ADRs, design notes, or preparing commit text.
Teams using repo-writing should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/repo-writing/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How repo-writing Compares
| Feature / Agent | repo-writing | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Applies Robota's repository writing rules for `.design/`, general documentation, and conventional commit messages. Use when editing docs, ADRs, design notes, or preparing commit text.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Repository Writing ## Rule Anchor - `AGENTS.md` > "Language Policy" - `AGENTS.md` > "Git Operations" - `AGENTS.md` > "Rules and Skills Boundary" ## Use This Skill When - Editing documentation or design notes. - Writing or reviewing `.design/` documents. - Preparing commit messages. - Deciding whether generated docs should be edited directly. ## Preconditions - Identify the target file path. - Determine whether the file is under `.design/`. - Determine whether the output is a document, generated file, or commit message. ## Execution Steps 1. Classify the target: - `.design/` document - general repository document - generated documentation - commit message 2. Apply the language rule: - `.design/` in Korean - repository documents outside `.design/` in English - commit messages in English 3. If the target is generated docs, update the source or generator instead of editing generated output directly. 4. If the target is a commit message, keep it in conventional commit format and focus on what changed for users or maintainers. 5. Keep examples and surrounding prose aligned with the target language of the document. ## Stop Conditions - A `.design/` document is written in English. - A non-`.design/` repository document is written in Korean. - Generated docs are edited directly. - A commit message is not in English or not in conventional format. ## Checklist - [ ] Target path is classified correctly before writing. - [ ] Language matches repository policy for that location. - [ ] Generated docs are changed through sources, not direct edits. - [ ] Commit messages use conventional commit format. - [ ] Commit titles focus on outcome rather than implementation trivia. ## Focused Examples ```text feat(agents): add ownerPath validation to tool execution fix(agent-runtime): stop implicit retry after failed transition docs(design): document harness migration phases ``` ```text .design/tmp/ -> Korean packages/*/docs/ -> English README.md -> English ``` ## Anti-Patterns - Mixing Korean and English policy arbitrarily in the same document class. - Editing generated API reference files directly. - Writing commit titles as implementation diary entries. - Treating repository writing rules as optional style preferences. ## Related Harness Commands - Current: repository policy review, docs generator commands - Planned: `pnpm harness:scan`
Related Skills
spec-writing-standard
Use when creating a new SPEC.md or incrementally updating an existing one. Covers both initial authoring and the ongoing incremental-update workflow that keeps the spec live.
repo-change-loop
Runs the standard Robota change loop by identifying impact, building affected scope, running targeted verification, and summarizing residual risk. Use when making or reviewing repository changes that should end in an explicit verification result.
pnpm-monorepo-build
Provide pnpm monorepo build commands and workflow guidance. Use when running package builds, filtered builds, or discussing build order.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
vitest-testing-strategy
Defines a practical testing strategy for TypeScript and JavaScript using Vitest across unit, integration, and type-level tests. Use when adding features, refactoring, or preventing regressions with fast feedback loops.
version-management
All packages must have the same version. Use changesets for coordinated version bumps. Never version packages independently.
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
user-request-gate
Use immediately when the user requests any implementation, code change, feature addition, fix, or modification. Gates code writing behind a backlog draft document. Read-only exploration is always permitted.
type-boundary-and-ssot
Applies Robota's preferred workflow for trust-boundary validation, strict typing, quality gates, and owner-based SSOT reuse. Use when adding or reviewing type contracts, boundary parsing, shared contract ownership, or running quality checks.
tdd-red-green-refactor
Kent Beck's TDD workflow. Use when writing new code or modifying existing behavior. Enforces the Red-Green-Refactor cycle with small, verifiable steps.