Research External

Primary Tool: Context7 MCP for library documentation

When to Use

• ALWAYS before implementing with external libraries
• When plan-task identifies technologies (Prisma, NestJS, etc.)
• When encountering unfamiliar APIs
• When version-specific behavior matters

Process

1. Check Research Cache First

# Before researching, check if we already have cached info
cat .claude/ledger/research/{technology}.md

If cache exists AND version matches → use cached info, skip research.

2. Use Context7 MCP

This is the primary research method. Context7 provides up-to-date library documentation.

Context7 queries:
- "Prisma 7 schema syntax generator client"
- "NestJS 11 module configuration providers"
- "class-validator decorator options"
- "BullMQ queue processor patterns"

Query tips:

• Include version number
• Be specific about the feature/API
• Search for examples, not just reference

3. Document Findings

Save to .claude/ledger/research/{technology}.md:

# {Technology} Research Cache

**Version:** {version}
**Updated:** {date}
**Source:** Context7 MCP

## Key APIs Used

### {Feature 1}

// Example from docs

**Notes:**
- Important gotcha 1
- Version-specific behavior

### {Feature 2}
...

## Integration Notes

- How it works with NestJS
- Required configuration
- Common patterns

## Gotchas

1. Issue 1 and solution
2. Issue 2 and solution

Technologies We Use (Reference)

When Context7 Isn't Enough

If Context7 doesn't have the info:

1. Check official docs URL (save URL for reference)
2. Check GitHub repo issues/discussions
3. Document source in research cache

Critical Rules

1. NEVER assume API syntax - always verify with Context7
2. ALWAYS check version - APIs change between versions
3. ALWAYS save to research cache - avoid repeated lookups
4. ALWAYS note gotchas - save time for future tasks

Output

Research produces:

• Updated .claude/ledger/research/{technology}.md
• Specific code examples ready to use
• Known gotchas documented