Documentation Generator

What It Does

Documentation Generator guides an AI agent through producing, auditing, co-authoring, and maintaining software documentation of any type. Covers eleven documentation phases across four major workflows, each with a dedicated reference file and named methodology.

Methodology

1. Audit and Plan: inventory existing docs, identify gaps, prioritise by impact
2. README: five-question structure; quality bar; tested quickstart command
3. API Documentation: TypeDoc, pdoc, godoc, Rust doc, OpenAPI/Redocly
4. Architecture: C4 model, Mermaid diagrams, ADRs; always explain the why
5. Code Comments: JSDoc/TSDoc, Python Google style; when to comment and when not to
6. Changelog: conventional format, git-cliff automation
7. Wiki and Knowledge Base: folder structure, runbooks, onboarding guides
8. AI-Readability: llms.txt, llms-full.txt, chunking, image alt-text
9. Codebase Documentation: discovery to structuring to 10-section technical manual from source
10. Co-Authoring: three-stage interactive workflow - context gathering, section refinement, reader testing
11. Agentic Spec: five-step spec folder scaffolding; living versioned folder with For-AI-Agents section

Example Use Cases

• New project: scaffold a spec folder before writing any code
• Existing codebase: extract a comprehensive technical manual
• Writing a PRD or RFC: co-author it interactively with reader testing
• Release prep: generate a changelog and verify all APIs are documented

Sample Output

documentation/SKILL.md (186 lines), references/generation-workflow.md (349 lines, Phases 1-8), codebase-documentation.md (174 lines), coauthoring-workflow.md (262 lines), agentic-spec-workflow.md (170 lines), agentic-spec-templates.md (608 lines, 7 templates).

Quickstart: ask the agent to generate API docs or help write a PRD and the relevant phase loads automatically.

Requirements

• Terminal access for codebase discovery commands (Phase 9)
• Read access to the source repository
• Optional: Git for changelog generation; issue tracker for OPEN items in specs

Documentation workflow

Documentation Generator guides an AI agent through producing, auditing, co-authoring, and maintaining software documentation of any type. It covers eleven documentation phases across four major workflows, each with dedicated reference material and explicit routing guidance.

Supported routes

• README, API docs, architecture docs, changelogs, wiki, and AI-readable docs
• comprehensive technical manuals generated from existing codebases
• interactive co-authoring for specs, RFCs, decision docs, and proposals
• agentic spec-folder scaffolding for spec-driven development

Documentation lookup policy

• Context7: use proactively for third-party library/API docs, setup steps, configuration details, and code-generation grounding when it is available.
• Astro Docs MCP: if the task is Astro-specific, use it first for Astro APIs, integrations, setup, config, import paths, and version-specific behavior when it is available.
• Official live web sources via search/fetch: still use these for freshness-sensitive public facts such as latest versions, release dates, deprecations, migration notes, or current support status.
• Fallback order: MCP docs first for structured reference; official live web sources via search/fetch second for freshness; local repo docs, code, and tests for project-specific behavior.

What the package includes

This download packages the documentation skill layer plus its workflow/reference files. It does not depend on a hosted service to function. Optional tools such as Git or an issue tracker may improve specific documentation routes (for example changelog generation or OPEN-item tracking), but they are not required to install the package.