Code Documenter
Writes docstrings, JSDoc, OpenAPI specs, API docs and user guides, then checks the examples.
- Repository
- Jeffallan/claude-skills
- Stars
- 12,176
- Licence
- MIT
- Files
- 9 files
What it does
Once installed, the agent works as a documentation specialist. It can add docstrings and JSDoc comments to code, write OpenAPI/Swagger API specs, set up documentation sites, and draft getting-started guides and tutorials. It first asks which documentation style you prefer, detects your language and framework, and then tries to verify code examples by running standard tools such as doctest, tsc and the Redocly linter.
Great for
- Developers who need docstrings or JSDoc added across an existing codebase
- Teams publishing REST API documentation from FastAPI, Django, NestJS or Express
- Maintainers who want a coverage summary of what is still undocumented
Skip it if
- Projects where the agent should not execute commands, since the validation step runs linters and doc tools on your code (review first)
- Non-technical users who just want a quick text summary; the skill is aimed at code and API documentation
Try asking
- “Add Google-style docstrings to all public functions in src/billing.py”
- “Create an OpenAPI 3.1 spec for our Express orders API”
- “Write a getting-started guide for our CLI tool with examples”
- “Set up a MkDocs documentation site for this Python package”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 9 original files, the MIT licence and an attribution note.
code-documenter.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip code-documenter.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip code-documenter.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- State your preferred docstring style (Google, NumPy or Sphinx) up front, since the skill asks before starting.
- Name your framework explicitly so the agent picks the correct API documentation approach.
- Review generated examples before merging; the skill says it validates them, but confirm the tools ran in your environment.
What's inside
- references/api-docs-fastapi-django.md
- references/api-docs-nestjs-express.md
- references/coverage-reports.md
- references/documentation-systems.md
- references/interactive-api-docs.md
- references/python-docstrings.md
- references/typescript-jsdoc.md
- references/user-guides-tutorials.md
- SKILL.md
Redistributed unmodified from Jeffallan/claude-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.