Skip to content
All Skills

Codebase Documenter

Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.

Software Engineering|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "codebase-documenter-54693f99" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# Codebase Documenter

Generates comprehensive documentation for codebases - architecture, components, data flow, development guidelines.

## When to Use

- "explain this codebase"
- "document the architecture"
- "how does this code work"
- "create developer documentation"
- "generate codebase overview"
- "create onboarding docs"

## What It Documents

### 1. Project Overview
- Purpose & vision
- Target users
- Key features
- Technology stack
- Project status

### 2. Architecture
- High-level structure
- Design patterns
- Data flow
- Control flow
- Diagrams (Mermaid)
- Architectural decisions

### 3. Directory Structure
- Organization purpose
- Naming conventions
- Entry points
- Core modules
- Configuration locations

### 4. Key Components
- Major modules
- Classes & functions
- Responsibilities
- Interactions
- Extension points
- Code examples

### 5. External Integrations
- APIs consumed
- Databases & schemas
- Authentication
- Caching
- Message queues
- File storage

### 6. Data Models
- Database schema
- Data structures
- Validation
- Migrations
- Data transformations

### 7. Development Setup
- Prerequisites
- Installation steps
- Configuration
- Running the app
- Testing
- Debugging
- Troubleshooting

### 8. Development Guidelines
- Coding conventions
- Testing approach
- Error handling
- Logging
- Security practices
- Performance patterns

### 9. Deployment
- Build process
- Deployment steps
- Environments
- Monitoring
- Rollback procedures

### 10. Contributing
- Development workflow
- Code review guidelines
- Testing requirements
- Documentation updates

## Approach

1. **Explore** using Explore agent (thorough)
2. **Map structure** with Glob
3. **Read critical files** (README, entry points, core modules)
4. **Identify patterns** with Grep (imports, exports)
5. **Trace execution** paths
6. **Extract knowledge** from docs, comments, tests
7. **Synthesize** into cohesive documentation

## Output

Creates markdown documentation:
```
docs/
├── README.md              # Overview and quick start
├── ARCHITECTURE.md        # System architecture
├── DEVELOPMENT.md         # Development guide
├── API.md                 # API documentation
├── DEPLOYMENT.md          # Deployment guide
└── CONTRIBUTING.md        # Contribution guidelines
```

Or single comprehensive doc if preferred.

## Depth Levels

- **Quick**: High-level overview (15-30 min)
- **Standard**: Comprehensive coverage (30-60 min)
- **Deep**: Exhaustive with examples (60+ min)

## Visual Elements

- Mermaid diagrams (architecture, flow charts, sequence)
- Code examples from codebase
- Specific file:line references
- Tables for structured info
- Lists for guidelines

## Tools Used

- **Task (Explore agent)**: Codebase exploration
- **Glob**: Map directory structure
- **Grep**: Find patterns, imports, exports
- **Read**: Analyze key files
- **Write**: Create documentation
- **Bash**: Extract metadata (git log, versions)

## Success Criteria

- Complete coverage of all areas
- Clear explanations with examples
- Visual diagrams for complex concepts
- Specific file:line references
- Actionable setup/development instructions
- New developer can onboard using only docs
- Organized, navigable structure
- Accurate and current information

## Integration

- **code-auditor**: Includes quality/security context
- **project-bootstrapper**: Documents bootstrap decisions
- **visual-html-creator**: Create visual diagrams
#broad-capability#engineering-workflow#productivity#visual-documentation#documentationgit

Related Skills

More skills in Software Engineering

Accessibility Standards

Comprehensive web accessibility standards based on WCAG 2.2 AA, with 38+ anti-patterns, legal enforcement context (EAA, ADA Title II), WAI-ARIA patterns, and framework-specific fixes for modern web frameworks and libraries.

#github-copilot#accessibilityMIT

Accord

Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision → L1 Requirements → L2 Team Detail → L3 Acceptance Criteria). No code. Use when authoring cross-team specs, building L0-L3 packages, or aligning Biz/Dev/Design on a single source of truth.

#broad-capability#developmentMIT

Acquire Codebase Knowledge

Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.

#github-copilot#documentationMIT

Acreadiness Assess

Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.

#github-copilot#planningMIT

Acreadiness Generate Instructions

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.

#github-copilot#skillMIT

Acreadiness Policy

Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.

#github-copilot#planningMIT