documentation-engineer
Technical documentation expert for creating clear, comprehensive documentation. Use when user asks to write docs, create README, or document code.
Works with
---
name: documentation-engineer
description: Technical documentation expert for creating clear, comprehensive documentation. Use when user asks to write docs, create README, or document code.
license: MIT
---
# Documentation Engineer
Expert in creating clear, comprehensive, and maintainable technical documentation.
## When This Skill Activates
Activates when you:
- Ask to write documentation
- Request README creation
- Mention "docs" or "document this"
- Need API documentation
## Documentation Types
### 1. README
Every project should have a README with:
```markdown
# Project Name
Brief description (what it does, why it exists)
## Quick Start
Installation and usage in 3 steps or less.
## Installation
Detailed installation instructions.
## Usage
Examples of common usage patterns.
## Configuration
Environment variables and configuration options.
## Development
How to run tests, build, and develop locally.
## Contributing
Guidelines for contributors.
## License
License information.
```
### 2. API Documentation
For each endpoint/function:
- **Description**: What it does
- **Parameters**: Name, type, required/optional, description
- **Return value**: Type and structure
- **Errors**: Possible errors and conditions
- **Examples**: Usage examples
### 3. Code Comments
Comment **why**, not **what**:
```typescript
// Bad: Sets the count to zero
count = 0;
// Good: Reset count for new measurement cycle
count = 0;
// Bad: Check if user is admin
if (user.role === 'admin') {
// Good: Only admins can bypass approval workflow
if (user.role === 'admin') {
```
### 4. Architecture Documentation
- System overview
- Component relationships
- Data flow
- Design decisions
- Trade-offs considered
## Documentation Principles
1. **Be Clear**: Use simple, direct language
2. **Be Concise**: Respect the reader's time
3. **Be Accurate**: Keep docs in sync with code
4. **Be Complete**: Cover all public interfaces
5. **Be Current**: Update docs when code changes
## Writing Guidelines
### Headings
- Use sentence case for headings
- Start with a verb or noun
- Be descriptive
### Code Examples
- Show before/after when appropriate
- Include import statements
- Show expected output
- Handle edge cases
### Links
- Use relative links for internal docs
- Include anchors for sections
- Test that links work
### Diagrams
- Use Mermaid for flowcharts and sequences
- Keep diagrams simple
- Add a title and legend
## Documentation Checklist
### README
- [ ] Project description
- [ ] Quick start guide
- [ ] Installation instructions
- [ ] Usage examples
- [ ] Configuration guide
- [ ] Contributing guidelines
### Code Docs
- [ ] All public functions documented
- [ ] Parameters and returns documented
- [ ] Examples provided for complex functions
- [ ] Edge cases documented
### API Docs
- [ ] All endpoints documented
- [ ] Request/response schemas
- [ ] Authentication requirements
- [ ] Error responses documented
- [ ] Rate limits documented
## Scripts
Generate documentation structure:
```bash
python3 scripts/generate_docs.py --name <service-name> --output docs/README.md
```
Validate documentation:
```bash
python3 scripts/validate_docs.py --input docs/README.md
```
## References
- `references/readme-template.md` - README template
- `references/api-template.md` - API documentation template
- `references/style-guide.md` - Documentation style guideMore Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

