research-first
This skill should be used when the user asks about frameworks (React, Next.js, FastAPI, PydanticAI, Supabase, LiveKit, LlamaIndex, Tailwind, Zustand, etc.), when implementing new features, when expressing uncertainty ("how do I", "what's the best way", "should I", "is this right"), when designing solutions or architecture, or before committing to any implementation approach. Spawns a research sub-agent to query context7 (framework docs) and Perplexity (solution validation) in a separate context window, returning concise findings to keep the main context clean.
npx skills add majiayu000/claude-skill-registry --skill research-first --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Research-First Skill Spawn a research sub-agent before implementation to ensure current best practices and validated approaches. ## Why This Skill Exists LLM knowledge has a cutoff date. Frameworks evolve rapidly. What was best practice 6 months ago may be deprecated today. This skill ensures: 1. **Current documentation** via context7 (real-time framework docs) 2. **Validated approaches** via Perplexity (cross-referenced solutions) 3. **Clean main context** by running research in a separate context window ## When to Use ### Automatic Triggers Invoke this skill when encountering: | Trigger Type | Examples | |--------------|----------| | Framework mentions | React, Next.js, FastAPI, PydanticAI, Supabase, LiveKit, LlamaIndex, Tailwind, Zustand, Playwright, etc. | | Uncertainty phrases | "how do I", "what's the best way", "should I", "is this the right approach" | | Implementation start | "implement", "build", "create", "add feature" + any technology | | Solution design | Architecture decisions, choosing between approaches | | API usage | Using any library API not used in current session | | Version concerns | Deprecation warnings, version mismatches, "latest" patterns | ### Proactiv
- Why This Skill Exists
- When to Use
- Automatic Triggers
- Proactive Use
- How to Use
- Step 1: Identify the Research Query
- Step 2: Spawn Research Sub-Agent
- Step 3: Apply Findings
- Research Patterns
- Pattern 1: Framework Documentation Lookup
- Pattern 2: Solution Design Validation
- Pattern 3: Solution Design Validation with Reasoning
- Pattern 4: Deep Research
- Pattern 5: Combined Research
What does the research-first skill do?
This skill should be used when the user asks about frameworks (React, Next.js, FastAPI, PydanticAI, Supabase, LiveKit, LlamaIndex, Tailwind, Zustand, etc.), when implementing new features, when expressing uncertainty ("how do I", "what's the best way", "should I", "is this right"), when designing solutions or architecture, or before committing to any implementation approach. Spawns a research sub-agent to query context7 (framework docs) and Perplexity (solution validation) in a separate context window, returning concise findings to keep the main context clean.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill research-first --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.