Skip to content
cccskills
FreePublished on GitHub

mk:docs-init

Use when a project has no docs/ directory or needs initial documentation generated from codebase analysis. Triggers on "init docs", "create documentation", "generate docs", "docs init", or when docs/ is empty. Do NOT use for updating existing docs (use mk:document-release).

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md3.6 KB
  • references/gotchas.md1.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Docs Init

Generate initial project documentation from codebase analysis.

Scope: Creates docs/ from scratch. For updating existing docs → mk:document-release.

Also run mk:project-context to generate the agent-constitution file (docs/project-context.md). mk:docs-init generates the full documentation suite; mk:project-context generates only the constitution.

When to Use

  • Project has no docs/ directory
  • docs/ exists but is empty or has only stubs
  • User asks to "initialize docs", "create documentation", "generate docs"
  • After mk:bootstrap completes (new project needs docs)

Do NOT invoke when: docs already exist and need updating (use mk:document-release).

Process

  1. Check existing state — does docs/ exist? Are files already populated?
    • If populated docs exist → suggest mk:document-release instead, stop.
  2. Scout codebase — activate mk:scout to analyze project structure. Skip: .claude/, .git/, node_modules/, __pycache__/, dist/, build/
  3. Merge findings — consolidate scout reports into context for doc generation
  4. Generate docs — spawn documenter subagent via Task tool with scout context. Output files (adapt to what the project actually has):
    • README.md — project overview (≤300 lines)
    • docs/project-overview.md — what this project is, who it's for
    • docs/codebase-summary.md — directory map, key modules, entry points
    • docs/code-standards.md — conventions found in codebase
    • docs/architecture/system-architecture.md — component diagram, data flow Optional (generate only if relevant):
    • docs/deployment-guide.md — if CI/CD or Docker config detected
    • docs/design-guidelines.md — if frontend/UI code detected
  5. Size check — run wc -l docs/*.md | sort -rn. Flag files >800 lines.
  6. Report — print generated files list with line counts.

Hard gate: Do NOT write code or implementation. Only documentation.

Gotchas

  • Hallucinating architecture: generating docs about code that doesn't exist → always scout FIRST, generate from findings only
  • Over-documenting small projects: creating 7 docs for a 50-line script → check project size; small projects get README + codebase-summary only
  • Stale on first run: docs describe initial state but drift immediately → tell user to run mk:document-release after each feature ship

Full list: references/gotchas.md

Workflow Integration

Runs after mk:bootstrap or on any existing project without docs.

mk:bootstrap → mk:docs-init → mk:plan-creator (first feature)

Also invoked standalone: mk:docs-init on existing undocumented project.

Handoff Protocol

On completion:

  • Print generated files list + line counts
  • "Docs initialized. Run mk:document-release after shipping features to keep them in sync."

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use this skill to generate well-branded interfaces and assets for MeowKit (AI Agent Toolkit for Claude Code), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Turn a raw idea into ONE honest recommendation: interview one question at a time until confirmed, then give a verdict with trade-offs and a checklist. Not for options or debate.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Browser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Detects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Angular v20+ patterns: components, signals, services, forms, routing, HTTP, testing, SSR. Auto-activates on .ts files in Angular projects (angular.json detected).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Design and review durable REST, GraphQL, RPC, or event API contracts: shape, compatibility, pagination, error semantics. Discovers existing consumers first. Not implementation, schema, or release.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

See all skills by ngocsangyem

Report a problem with this skill