メニュー
AI-powered web search, research, and reasoning via Perplexity
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
How to use AI APIs like OpenAI, ChatGPT, Elevenlabs, etc. When a user asks you to make an app that requires an AI API, use this skill to understand how to use the API or how to respond to the user.
Debug Gemini/GPT vision API issues in puzzle image extraction
Constraint satisfaction patterns for the Pips puzzle solver
Create git commits with user approval and no Claude attribution
Create or update continuity ledger for state preservation across clears
| name | perplexity-search |
| description | AI-powered web search, research, and reasoning via Perplexity |
| allowed-tools | ["Bash","Read"] |
Web search with AI-powered answers, deep research, and chain-of-thought reasoning.
| Model | Purpose |
|---|---|
sonar | Lightweight search with grounding |
sonar-pro | Advanced search for complex queries |
sonar-reasoning-pro | Chain of thought reasoning |
sonar-deep-research | Expert-level exhaustive research |
uv run python scripts/perplexity_search.py \
--ask "What is the latest version of Python?"
uv run python scripts/perplexity_search.py \
--search "SQLite graph database patterns" \
--max-results 5 \
--recency week
uv run python scripts/perplexity_search.py \
--research "compare FastAPI vs Django for microservices"
uv run python scripts/perplexity_search.py \
--reason "should I use Neo4j or SQLite for small graph under 10k nodes?"
uv run python scripts/perplexity_search.py \
--deep "state of AI agent observability 2025"
| Parameter | Description |
|---|---|
--ask | Quick question with AI answer (sonar) |
--search | Direct web search - ranked results without AI synthesis |
--research | AI-synthesized research (sonar-pro) |
--reason | Chain-of-thought reasoning (sonar-reasoning-pro) |
--deep | Deep comprehensive research (sonar-deep-research) |
| Parameter | Description |
|---|---|
--max-results N | Number of results (1-20, default: 10) |
--recency | Filter: day, week, month, year |
--domains | Limit to specific domains |
| Need | Use | Why |
|---|---|---|
| Quick fact | --ask | Fast, lightweight |
| Find sources | --search | Raw results, no AI overhead |
| Synthesized answer | --research | AI combines multiple sources |
| Complex decision | --reason | Chain-of-thought analysis |
| Comprehensive report | --deep | Exhaustive multi-source research |
# Find recent sources on a topic
uv run python scripts/perplexity_search.py \
--search "OpenTelemetry AI agent tracing" \
--recency month --max-results 5
# Get AI synthesis
uv run python scripts/perplexity_search.py \
--research "best practices for AI agent logging 2025"
# Make a decision
uv run python scripts/perplexity_search.py \
--reason "microservices vs monolith for startup MVP"
# Deep dive
uv run python scripts/perplexity_search.py \
--deep "comprehensive guide to building feedback loops for autonomous agents"
Requires PERPLEXITY_API_KEY in environment or ~/.claude/.env.