External Research Workflow Research external sources (documentation, web, APIs) for libraries, best practices, and general topics. Note: The current year is 2025. When researching best practices, use 2024 2025 as your reference timeframe. Invocation Question Flow (No Arguments) If the user types just /research external with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase. Phase 1: Research Type Mapping: "How to use library" → library focus "Best practices" → best practices focus "General topic" → general focus "Compare options" → best practices with comparison framing Phase 2: Specific Topic Examples of good answers: "How to use Prisma ORM with TypeScript" "Best practices for error handling in Python" "React vs Vue vs Svelte for dashboards" Phase 3: Library Details (if library focus) If user selected library focus: Then ask for specific library name if not already provided. Phase 4: Depth Mapping: "Quick answer" → depth shallow "Thorough" → depth thorough Phase 5: Output Mapping: "Research document" → output doc "Handoff" → output handoff Summary Before Execution Focus Modes (First Argument) Focus Primary Tool Purpose library nia docs API docs, usage patterns, code examples best practices perplexity search Recommended approaches, patterns, comparisons general All MCP tools Comprehensive multi source research Options Option Values Description topic "string" Required. The topic/library/concept to research depth shallow , thorough Search depth (default: shallow) output handoff , doc Output format (default: doc) library "name" For library focus: specific package name registry npm , py pi , crates , go modules For library focus: package registry Workflow Step 1: Parse Arguments Extract from user input: Step 2: Execute Research by Focus Focus: library Primary tool: nia docs Find API documentation, usage patterns, code examples. Thorough depth additions: Multiple semantic queries with variations Grep for specific function/class names Scrape official documentation pages Focus: best practices Primary tool: perplexity search Find recommended approaches, patterns, anti patterns. Thorough depth additions: Focus: general Use ALL available MCP tools comprehensive multi source research. Step 2a: Library documentation (nia docs) Step 2b: Web research (perplexity) Step 2c: Specific documentation (firecrawl) Thorough depth additions: Run all three tools with expanded queries Cross reference findings between sources Follow links from initial results for deeper context Step 3: Synthesize Findings Combine results from all sources: 1. Key Concepts Core ideas and terminology 2. Code Examples Working examples from documentation 3. Best Practices Recommended approaches 4. Pitfalls Common mistakes to avoid 5. Alternatives Other options considered 6. Sources URLs for all citations Step 4: Write Output Output: doc (default) Write to: thoughts/shared/research/YYYY MM DD {topic slug}.md {language} // Working examples found Output: handoff Write to: thoughts/shared/handoffs/{session}/research {topic slug}.yaml Step 5: Return Summary Error Handling If an MCP tool fails (API key missing, rate limited, etc.): 1. Log the failure in output: 2. Continue with other sources partial results are valuable 3. Set status appropriately: complete All requested tools succeeded partial Some tools failed, findings still useful failed No useful results obtained 4. Note gaps in findings: Examples Library Research (Shallow) Best Practices (Thorough) General Research for Handoff Quick Library Lookup Integration with Other Skills After Research Use Skill For output handoff plan agent Create implementation plan Code examples found implement task Direct implementation Architecture decision create plan Detailed planning Library comparison Present to user Decision making Required Environment NIA API KEY or nia server in mcp config.json PERPLEXITY API KEY in environment or ~/.claude/.env FIRECRAWL API KEY and firecrawl server in mcp config.json Notes NOT for codebase exploration Use research codebase or scout for that Always cite sources Include URLs for all findings 2024 2025 timeframe Focus on current best practices Graceful degradation Partial results better than no results

research-external