Tavily Agent Skills
Web search, content extraction, site crawling, URL discovery, and deep research — powered by the Tavily CLI.
Installation
Install skills
# Agent skills (Claude Code, Cursor, etc.)
npx skills add https://github.com/tavily-ai/skillsInstall the Tavily CLI
The skills require the Tavily CLI (tvly) to be installed. It lives in its own repository: tavily-ai/tavily-cli.
curl -fsSL https://cli.tavily.com/install.sh | bashOr install manually:
uv tool install tavily-cli # or: pip install tavily-cliAuthenticate
tvly login --api-key tvly-YOUR_KEY
# or: tvly login (opens browser for OAuth)
# or: export TAVILY_API_KEY=tvly-...Get an API key at tavily.com.
Available Skills
| Skill | Description |
|---|---|
| tavily-search | Search the web with LLM-optimized results. Supports domain filtering, time ranges, and multiple search depths. |
| tavily-extract | Extract clean markdown/text content from specific URLs. Handles JS-rendered pages. |
| tavily-crawl | Crawl websites and extract content from multiple pages. Save as local markdown files. |
| tavily-map | Discover all URLs on a website without extracting content. Faster than crawling. |
| tavily-research | Comprehensive AI-powered research with citations. Multi-source synthesis in 30-120s. |
| tavily-cli | Overview skill with workflow guide, install/auth instructions. |
| tavily-best-practices | Reference docs for building production-ready Tavily integrations. |
Workflow
Start simple, escalate when needed:
- Search — Find pages on a topic (
tvly search "query" --json) - Extract — Get content from a specific URL (
tvly extract "https://..." --json) - Map — Discover URLs on a site (
tvly map "https://..." --json) - Crawl — Bulk extract from a site section (
tvly crawl "https://..." --output-dir ./docs/) - Research — Deep multi-source analysis (
tvly research "topic" --model pro)