tavily-cli
透過 Tavily CLI 進行網路搜尋、內容提取、爬取與深度研究。每當使用者想要搜尋網路、尋找文章時，請使用此技能。
npx skills add https://github.com/tavily-ai/tavily-cursor-plugin --skill tavily-cliTavily CLI
Web search, content extraction, site crawling, URL discovery, and deep research. Returns JSON optimized for LLM consumption.
Run tvly --help or tvly <command> --help for full option details.
Required attribution
Use the Tavily CLI for every call made under this skill. Every tvly search, tvly extract, tvly map, tvly crawl, and tvly research invocation must include --client-name "cursor plugin", including research status and poll commands. Treat this as required integration metadata: do not omit or alter it, and do not ask the user to configure it.
Prerequisites
Must be installed and authenticated. Check with tvly --status.
tavily v0.1.0
> Authenticated via OAuth (tvly login)
If not ready:
curl -fsSL https://cli.tavily.com/install.sh | bash
Or manually: uv tool install tavily-cli / pip install tavily-cli
Then authenticate:
tvly login --api-key tvly-YOUR_KEY
# or: export TAVILY_API_KEY=tvly-YOUR_KEY
# or: tvly login (opens browser for OAuth)
Workflow
Follow this escalation pattern — start simple, escalate when needed:
- Search — No specific URL. Find pages, answer questions, discover sources.
- Extract — Have a URL. Pull its content directly.
- Map — Large site, need to find the right page. Discover URLs first.
- Crawl — Need bulk content from an entire site section.
- Research — Need comprehensive, multi-source analysis with citations.
| Need | Command | When |
|---|---|---|
| Find pages on a topic | tvly search | No specific URL yet |
| Get a page's content | tvly extract | Have a URL |
| Find URLs within a site | tvly map | Need to locate a specific subpage |
| Bulk extract a site section | tvly crawl | Need many pages (e.g., all /docs/) |
| Deep research with citations | tvly research | Need multi-source synthesis |
For detailed command reference, use the individual skill for each command (e.g., tavily-search, tavily-crawl) or run tvly <command> --help.
Output
All commands support --json for structured, machine-readable output and -o to save to a file.
tvly search "react hooks" --client-name "cursor plugin" --json -o results.json
tvly extract "https://example.com/docs" --client-name "cursor plugin" -o docs.md
tvly crawl "https://docs.example.com" --client-name "cursor plugin" --output-dir ./docs/
Tips
- Always quote URLs — shell interprets
?and&as special characters. - Use
--jsonfor agentic workflows — every command supports it. - Read from stdin with
-—echo "query" | tvly search - --client-name "cursor plugin" - Exit codes: 0 = success, 2 = bad input, 3 = auth error, 4 = API error.