exa
High-precision semantic search and content retrieval via Exa API. Use when: (1) Deep research requiring semantic understanding, (2) Code documentation and examples lookup, (3) Company/professional research, (4) AI-powered comprehensive research tasks, (5) URL content extraction with structured output. Triggers: "research", "find papers", "code examples", "company info", "LinkedIn profiles", "deep analysis". Differentiator: Exa excels at semantic/neural search while grok-search is better for real-time news and general web content.
npx skills add majiayu000/claude-skill-registry --skill exa-dianel555-dskills --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.
# Exa Search High-precision semantic search via Exa API. Standalone CLI only (no MCP dependency). ## Execution Method Run `scripts/exa_cli.py` via Bash: ```bash # Prerequisites: pip install httpx tenacity # Environment: EXA_API_KEY (required), EXA_API_URL (optional, default: https://api.exa.ai) ``` ## Available Tools ### Search Tools ```bash # Basic semantic search python scripts/exa_cli.py web_search_exa --query "emerging patterns in TypeScript" [--num-results 10] [--type auto|keyword|neural] [--livecrawl always|fallback|never] # Advanced search with filters python scripts/exa_cli.py web_search_advanced_exa --query "machine learning papers" \ [--include-domains arxiv.org,github.com] [--exclude-domains medium.com] \ [--start-date 2024-01-01] [--end-date 2024-12-31] \ [--text] [--highlights] [--summary] [--out results.json] # Deep search with query expansion python scripts/exa_cli.py deep_search_exa --objective "foundations of quantum error correction" [--additional-queries "query1|query2"] # Company research python scripts/exa_cli.py company_research_exa --company "Anthropic" [--num-results 10] # LinkedIn profile search python scripts/exa_cli.py linkedin_search_exa --query "AI rese
- Execution Method
- Available Tools
- Search Tools
- Content Tools
- Research Tools
- Configuration
- Tool Capability Matrix
- Tool Routing Guide
- Exa vs Grok-Search
- Workflow Patterns
- Pattern 1: Quick Semantic Search
- Pattern 2: Filtered Research
- Pattern 3: Deep Research Task
- Error Handling
Basic semantic search Advanced search with filters python scripts/exa_cli.py web_search_advanced_exa --query "machine learning papers" \ Deep search with query expansion python scripts/exa_cli.py deep_search_exa --objective "foundations of quantum error correction" [--additional-queries "query1|query2"] Company research python scripts/exa_cli.py company_research_exa --company "Anthropic" [--num-results 10] LinkedIn profile search python scripts/exa_cli.py linkedin_search_exa --query "AI researchers at Stanford" [--num-results 10] Extract content from URL
What does the exa skill do?
High-precision semantic search and content retrieval via Exa API. Use when: (1) Deep research requiring semantic understanding, (2) Code documentation and examples lookup, (3) Company/professional research, (4) AI-powered comprehensive research tasks, (5) URL content extraction with structured output. Triggers: "research", "find papers", "code examples", "company info", "LinkedIn profiles", "deep analysis". Differentiator: Exa excels at semantic/neural search while grok-search is better for real-time news and general web content.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill exa-dianel555-dskills --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.
