Code Documentation
Generate or improve READMEs, API references, architecture notes, changelogs, and developer guides from an existing codebase when onboarding or open-sourcing.
Overview
Code Documentation is an agent skill most often used in Build (also Ship review and Grow content prep) that generates READMEs, API references, architecture docs, changelogs, and developer guides from codebase analysis.
Install
npx skills add https://github.com/bytedance/deer-flow --skill code-documentationWhat is this skill?
- README.md with badges, install, usage, and API-style sections
- API reference and architecture documentation from source analysis
- Developer onboarding, contribution guides, and changelog generation
- Inline documentation conventions for JSDoc, docstrings, GoDoc, and similar
Adoption & trust: 827 installs on skills.sh; 70.7k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your repo works but lacks trustworthy README, API, or onboarding docs, so agents and humans cannot adopt or extend it safely.
Who is it for?
Indie devs shipping libraries, APIs, or SaaS repos who need fast, industry-shaped docs without hiring a technical writer first.
Skip if: Legal/compliance-only policy packs with no code to analyze, or marketing landing copy with no developer reference intent.
When should I use this skill?
User requests to document code, create a README, generate API docs, write a developer guide, or analyze a codebase for documentation purposes.
What do I get? / Deliverables
You get structured documentation—from README through API and contributor guides—aligned to your stack and ready to edit and publish.
- README.md or expanded doc set with install and usage
- API reference, architecture notes, changelog, or inline comment blocks as requested
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build/docs is the primary shelf because documentation is usually authored alongside or right after implementation. Docs subphase covers README generation, API reference, inline comments, and contributor guides—not runtime monitoring.
Where it fits
Draft README install and usage sections right after finishing an API or CLI feature.
Refresh architecture and changelog docs before tagging a release candidate.
Align public repo documentation with what you publish for SEO and developer discovery.
How it compares
Generator for repo-facing developer docs—not a substitute for automated OpenAPI linting or deployed doc-site hosting.
Common Questions / FAQ
Who is code-documentation for?
Solo builders and small teams who want an agent to draft README, API, architecture, and guide content from an existing codebase.
When should I use code-documentation?
In Build/docs after implementation; in Ship when tightening launch-readiness docs; in Grow when refreshing public README or developer content for distribution.
Is code-documentation safe to install?
It reads and summarizes your code locally through the agent; review the Security Audits panel on this Prism page and avoid pointing it at secrets-heavy trees without redaction.
SKILL.md
READMESKILL.md - Code Documentation
# Code Documentation Skill ## Overview This skill generates professional, comprehensive documentation for software projects, codebases, libraries, and APIs. It follows industry best practices from projects like React, Django, Stripe, and Kubernetes to produce documentation that is accurate, well-structured, and useful for both new contributors and experienced developers. The output ranges from single-file READMEs to multi-document developer guides, always matched to the project's complexity and the user's needs. ## Core Capabilities - Generate comprehensive README.md files with badges, installation, usage, and API reference - Create API reference documentation from source code analysis - Produce architecture and design documentation with diagrams - Write developer onboarding and contribution guides - Generate changelogs from commit history or release notes - Create inline code documentation following language-specific conventions - Support JSDoc, docstrings, GoDoc, Javadoc, and Rustdoc formats - Adapt documentation style to the project's language and ecosystem ## When to Use This Skill **Always load this skill when:** - User asks to "document", "create docs", or "write documentation" for any code - User requests a README, API reference, or developer guide - User shares a codebase or repository and wants documentation generated - User asks to improve or update existing documentation - User needs architecture documentation, including diagrams - User requests a changelog or migration guide ## Documentation Workflow ### Phase 1: Codebase Analysis Before writing any documentation, thoroughly understand the codebase. #### Step 1.1: Project Discovery Identify the project fundamentals: | Field | How to Determine | |-------|-----------------| | **Language(s)** | Check file extensions, `package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, etc. | | **Framework** | Look at dependencies for known frameworks (React, Django, Express, Spring, etc.) | | **Build System** | Check for `Makefile`, `CMakeLists.txt`, `webpack.config.js`, `build.gradle`, etc. | | **Package Manager** | npm/yarn/pnpm, pip/uv/poetry, cargo, go modules, etc. | | **Project Structure** | Map out the directory tree to understand the architecture | | **Entry Points** | Find main files, CLI entry points, exported modules | | **Existing Docs** | Check for existing README, docs/, wiki, or inline documentation | #### Step 1.2: Code Structure Analysis Use sandbox tools to explore the codebase: ```bash # Get directory structure ls /mnt/user-data/uploads/project-dir/ # Read key files read_file /mnt/user-data/uploads/project-dir/package.json read_file /mnt/user-data/uploads/project-dir/pyproject.toml # Search for public API surfaces grep -r "export " /mnt/user-data/uploads/project-dir/src/ grep -r "def " /mnt/user-data/uploads/project-dir/src/ --include="*.py" grep -r "func " /mnt/user-data/uploads/project-dir/ --include="*.go" ``` #### Step 1.3: Identify Documentation Scope Based on analysis, determine what documentation to produce: | Project Size | Recommended Documentation | |-------------|--------------------------| | **Single file / script** | Inline comments + usage header | | **Small library** | README with API reference | | **Medium project** | README + API docs + examples | | **Large project** | README + Architecture + API + Contributing + Changelog | ### Phase 2: Documentation Generation #### Step 2.1: README Generation Every project needs a