codebase-documenter

Audit codebase documentation gaps and propose concrete improvements before writing.

Updated Apr 26, 2026
One-click install
npx skills add https://github.com/XinheLIU/human-leverage --skill codebase-documenter-xinheliu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: codebase-documenter
Source: https://github.com/XinheLIU/human-leverage/tree/main/.claude/skills/codebase-documenter
Command: npx skills add https://github.com/XinheLIU/human-leverage --skill codebase-documenter-xinheliu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Auditing and generating documentation for large codebases is error-prone and time-consuming; this skill provides an audit-first approach to produce consistent README s, architecture diagrams (C4 in Mermaid), API references, and inline docstrings, with a proposal phase to confirm changes before writing.

Core Features & Use Cases

  • Audit existing docs to surface gaps across root README, docs/architecture, AGENTS rules, and references.
  • Propose concrete changes in Phase 2 and obtain user approval before applying them.
  • Generate documentation outputs using official templates (README.template.md, ARCHITECTURE.template.md, API.template.md, CODE_COMMENTS.template.md) and link to existing references.
  • Maintain alignment with doc-types-playbook and ADR references; avoid duplicating content and augment with cross-links.

Quick Start

Audit the repository to surface missing or outdated documentation and generate consistent docs via the templates.

Frequently Asked Questions about codebase-documenter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit my codebase documentation to find missing or outdated files?

Codebase documentation auditing scans existing artifacts like root READMEs, architecture diagrams, API references, and inline comments to surface gaps and inconsistencies. This audit-first approach identifies outdated content and missing elements before proposing concrete improvements.

What is the best way to generate C4 architecture diagrams in Mermaid for a software project?

Generating C4 architecture diagrams in Mermaid involves using established templates to structure system context, containers, and components. The process creates consistent, checked-in documentation that visually maps codebase architecture while linking directly to existing reference materials.

How do I generate consistent READMEs and API references without overwriting existing documentation?

Generating consistent READMEs and API references uses official templates like README.template.md and API.template.md to structure content. A proposal phase presents concrete diffs for user approval before applying changes, ensuring existing references are augmented with cross-links rather than duplicated.

Can I review proposed documentation changes before they are applied to my repository?

Reviewing proposed documentation changes before application is a core phase of the generation process. The system presents concrete diffs and proposals for user approval, ensuring you maintain control over content updates and checked-in documentation modifications before any writing occurs.

Does codebase documentation generation preserve Last updated metadata and ADR cross-links?

Codebase documentation generation preserves Last updated metadata and aligns with Architecture Decision Records (ADRs). It maintains existing reference links, avoids duplicating content across doc-types, and augments current documentation with accurate cross-links to ensure structural consistency.