1---
2name: tavily-cli
3description: |
4  Web search, content extraction, crawling, and deep research via the Tavily CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, extract content from a URL, grab text from a webpage, crawl documentation, download a site's pages, discover URLs on a domain, or conduct in-depth research with citations. Also use when they say "fetch this page", "pull the content from", "get the page at https://", "find me articles about", or reference extracting data from external websites. This provides LLM-optimized web search, content extraction, site crawling, URL discovery, and AI-powered deep research — capabilities beyond what agents can do natively. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.
5compatibility: Requires tavily-cli (`curl -fsSL https://cli.tavily.com/install.sh | bash`) and a Tavily API key from tavily.com.
6allowed-tools: Bash(tvly *)
7---
8 
9# Tavily CLI
10 
11Web search, content extraction, site crawling, URL discovery, and deep research. Returns JSON optimized for LLM consumption.
12 
13Run `tvly --help` or `tvly <command> --help` for full option details.
14 
15## Prerequisites
16 
17Must be installed and authenticated. Check with `tvly --status`.
18 
19```bash
20tavily v0.1.0
21 
22> Authenticated via OAuth (tvly login)
23```
24 
25If not ready:
26 
27```bash
28curl -fsSL https://cli.tavily.com/install.sh | bash
29```
30 
31Or manually: `uv tool install tavily-cli` / `pip install tavily-cli`
32 
33Then authenticate:
34 
35```bash
36tvly login --api-key tvly-YOUR_KEY
37# or: export TAVILY_API_KEY=tvly-YOUR_KEY
38# or: tvly login  (opens browser for OAuth)
39```
40 
41## Workflow
42 
43Follow this escalation pattern — start simple, escalate when needed:
44 
451. **Search** — No specific URL. Find pages, answer questions, discover sources.
462. **Extract** — Have a URL. Pull its content directly.
473. **Map** — Large site, need to find the right page. Discover URLs first.
484. **Crawl** — Need bulk content from an entire site section.
495. **Research** — Need comprehensive, multi-source analysis with citations.
50 
51| Need | Command | When |
52|------|---------|------|
53| Find pages on a topic | `tvly search` | No specific URL yet |
54| Get a page's content | `tvly extract` | Have a URL |
55| Find URLs within a site | `tvly map` | Need to locate a specific subpage |
56| Bulk extract a site section | `tvly crawl` | Need many pages (e.g., all /docs/) |
57| Deep research with citations | `tvly research` | Need multi-source synthesis |
58 
59For detailed command reference, use the individual skill for each command (e.g., `tavily-search`, `tavily-crawl`) or run `tvly <command> --help`.
60 
61## Output
62 
63All commands support `--json` for structured, machine-readable output and `-o` to save to a file.
64 
65```bash
66tvly search "react hooks" --json -o results.json
67tvly extract "https://example.com/docs" -o docs.md
68tvly crawl "https://docs.example.com" --output-dir ./docs/
69```
70 
71## Tips
72 
73- **Always quote URLs** — shell interprets `?` and `&` as special characters.
74- **Use `--json` for agentic workflows** — every command supports it.
75- **Read from stdin with `-`** — `echo "query" | tvly search -`
76- **Exit codes**: 0 = success, 2 = bad input, 3 = auth error, 4 = API error.
77