Last Updated: YYYY-MM-DD Next Review: YYYY-MM-DD (3 months from research date)

### Step 5: Update research/CLAUDE.md Index

**ALWAYS update research/CLAUDE.md** with an entry for the research.

The `research/CLAUDE.md` file is a **memory file** that Claude Code automatically loads. It serves as an index of all researched topics.

**Format Guidelines** (following Claude Code memory best practices):
- ✓ **Be specific**: Include concrete details, not vague descriptions
- ✓ **Use structure**: Format as bullet points under descriptive headings
- ✓ **Stay scannable**: Use clear sections and consistent formatting
- ✓ **Update regularly**: Keep status and dates current

Add a new entry under the "Research Index" heading:

```markdown
### <Topic Name> (`<topic>.md`)

**Researched:** YYYY-MM-DD
**Status:** Active
**When to Use:** Specific scenarios where this applies (be concrete)
**Summary:**
- Key point 1 with specific detail
- Key point 2 with specific detail
- Key point 3 with specific detail

Example entry:

### Python Asyncio (`python-asyncio.md`)

**Researched:** 2025-11-18
**Status:** Active
**When to Use:** Building concurrent I/O-bound applications, async web servers, or async database operations
**Summary:**
- Use `asyncio.create_task()` for fire-and-forget, `asyncio.gather()` for concurrent execution with results
- Always use `async with` for async context managers to ensure proper cleanup
- Avoid blocking calls in async functions - use `asyncio.to_thread()` for CPU-bound work

Step 6: Create TODO List

Use the TodoWrite tool to track research progress:

[
  {"content": "Check existing research in research/CLAUDE.md", "status": "completed", "activeForm": "Checking existing research"},
  {"content": "Execute Perplexity search for <topic>", "status": "completed", "activeForm": "Executing Perplexity search"},
  {"content": "Structure documentation in research/<topic>.md", "status": "in_progress", "activeForm": "Structuring documentation"},
  {"content": "Update research/CLAUDE.md research index", "status": "pending", "activeForm": "Updating research/CLAUDE.md research index"}
]

Documentation Categories

Framework Documentation

• React, Vue, Angular, Svelte
• Next.js, Nuxt, SvelteKit
• Express, FastAPI, Django

Language Documentation

• Python, JavaScript/TypeScript, Rust, Go
• Java, Kotlin, Swift
• Ruby, PHP, C#

Tool Documentation

• Docker, Kubernetes
• Git, GitHub Actions
• Webpack, Vite, esbuild

API Documentation

• REST API design
• GraphQL
• WebSockets

Best Practices

• Code patterns
• Architecture patterns
• Security practices
• Performance optimization

Output Quality Standards

Must Include

• ✓ Clear, scannable structure
• ✓ Code examples for key concepts
• ✓ Links to official documentation
• ✓ Best practices and anti-patterns
• ✓ Version information
• ✓ Common pitfalls and solutions

Avoid

• ✗ Large blocks of unformatted text
• ✗ Outdated information without version context
• ✗ Examples without explanation
• ✗ Missing links to sources
• ✗ Vague or generic advice

Example Queries That Trigger This Skill

• "Research Python asyncio documentation"
• "Find best practices for React hooks"
• "Look up TypeScript generics documentation"
• "What are the latest Docker best practices?"
• "Research how to implement WebSockets in Node.js"
• "Find documentation on Rust error handling"
• "Look up GraphQL schema design patterns"

Maintenance

Updating Existing Research

When updating research:

1. Read the existing file
2. Add a note at the top: **Updated:** YYYY-MM-DD - Reason for update
3. Update the "Last Updated" date
4. Update the "Next Review" date
5. Update the research/CLAUDE.md entry with new date

Deprecation

If documentation becomes outdated:

1. Update status to "Deprecated"
2. Add deprecation notice with replacement topic
3. Update research/CLAUDE.md status

Troubleshooting

Perplexity API Errors

Error: API key invalid

• Check PERPLEXITY_API_KEY environment variable
• Ensure you have a new API key that supports Search API

Error: Rate limit exceeded

• Wait before making additional requests
• Consider reducing result count with -n flag

Research Quality Issues

Too many irrelevant results

• Use domain filtering: -d "official-docs.com,github.com"
• Make query more specific
• Adjust recency filter: -r month

Missing official documentation

• Explicitly include official domain in search query
• Use -d flag to target specific authoritative sources

Best Practices

1. Always check existing research first - Avoid duplicate work
2. Use specific queries - "Python 3.12 asyncio patterns" vs "Python async"
3. Target authoritative sources - Use domain filtering for official docs
4. Structure consistently - Follow the documentation template
5. Include examples - Code examples make documentation actionable
6. Update research/CLAUDE.md - Keep the research index current
7. Set review dates - Mark when research should be refreshed
8. Track with TODOs - Use TodoWrite to show progress

Script Reference

The perplexity-research.sh script is located at:

.claude/skills/research-docs/scripts/perplexity-research.sh

Key Features:

• Pre-configured for documentation domains
• AI-optimized structured output
• Flexible filtering options
• Error handling and validation
• Multiple output formats

Default Documentation Domains:

• stackoverflow.com
• github.com
• docs.python.org
• developer.mozilla.org
• nodejs.org
• reactjs.org
• vuejs.org
• angular.io
• rust-lang.org
• go.dev
• kotlinlang.org
• dev.to
• medium.com

Override with -d flag for specific research needs.