tavily-search · tavily-ai, core — Claude Code skill: web search and page extraction
tavily-search — a skill for Claude Code that enables web searching and data extraction from webpages. Use it to verify facts, read current news, and gather information beyond the model's training data.
MIT 39,400 installs ★ 497 updated 2026-10-23
npx skills add tavily-ai/skills --skill tavily-search -a claude-codeWhat tavily-search does
The skill adds tools for web interaction: tavily_search, tavily_extract, tavily_map, and tavily_crawl. It allows the agent to search for information, extract text from pages, or crawl site sections. If tools are available via MCP, use them directly; otherwise, run the tvly CLI command.
Save results to the .tavily/ directory using the -o flag to avoid context overflow and enable file reuse. Formulate queries like a search engine, splitting complex questions into focused parts. When handling JavaScript-rendered pages or tables, set extract_depth to advanced.
What it helps with
- Verify current facts or news
- Extract content from a specific URL
- Gather data from all pages in a site section
- Retrieve information outside the model's training data
Example prompts for the agent
- tvly search 'latest Rust release date' --depth advanced --max-results 10
- tvly extract 'https://example.com/report' -o .tavily/report.json
How to install tavily-search
1Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a claude-code2Manually: put the files in place
~/.claude/skills/tavily-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/tavily-search/
1Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a codex2Manually: put the files in place
.agents/skills/tavily-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a cursor2Manually: put the files in place
.cursor/skills/tavily-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install tavily-ai/skills skills/core/tavily-search2Manually: put the files in place
.github/skills/tavily-search/SKILL.md1Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/tavily-ai/skills --path skills/core/tavily-searchManually: put the files in place
.devin/skills/tavily-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about tavily-search
How to install tavily-search in Claude Code?
Run npx skills add tavily-ai/skills --skill tavily-search -a claude-code in your project terminal.
What does tavily-search do?
It enables the agent to search the web, read URLs, and extract data when the model's training knowledge is insufficient.
What is required to run tavily-search?
The skill relies on tvly CLI or MCP tools, which must be available in your execution environment.
Source text
SKILL.md · MIT
---
name: tavily-search
description: |
Use this skill whenever a task needs the web: searching for information, checking current facts or news, finding sources, reading a URL, finding a page on a site, or collecting many pages from a site. Use it for anything past your training data or anything the user wants verified online.
allowed-tools: Bash(tvly *)
---
# Tavily search
Use the `tavily_search`, `tavily_extract`, `tavily_map` and `tavily_crawl` tools if your tool list has them
(some clients add a prefix such as `mcp__tavily__`). Otherwise run `tvly <command>` directly; there's no
need to check for it first. If neither works, follow [setup](references/setup.md).
Parameters are named as in the API (`max_results`). The CLI spells them as flags (`--max-results`) with
comma-separated lists (`--include-domains sec.gov,reuters.com`). For exact parameters, read the tool schema,
run `tvly <command> --help`, or see the [API reference](https://docs.tavily.com/documentation/api-reference/endpoint/search).
| You have | You need | Use |
|---|---|---|
| A question or topic | Sources, facts or news | Search |
| URLs | Their content | Extract |
| A site, not the exact page | The right page's URL | [Map](references/map.md) |
| A site section | Many of its pages | [Crawl](references/crawl.md) |
## Search
**Use advanced search.** Set `search_depth` to `advanced` (`--depth advanced` in the CLI) for every search
unless the user needs a fast answer to a simple lookup. It reaches more sources and ranks the passages that match your query.
**Write queries for a search engine.** Use the names and terms you expect on the page, not the user's whole
request. Split a question with several parts into one focused search per part. For a long written report,
search each part separately and extract the main sources for each before you write.
**Follow your leads.** When a result names a likely answer, test it right away: search that name with the
other details you know, or extract its page. Keep a lead that fits most details until a source contradicts it; a detail you can't confirm doesn't rule it out. When a search misses,
search the details again in their own words before adding names or filters you guessed, and build lists of
candidates from results, not memory. When a detail keeps coming back empty, work out what it refers to, such as
the role, event or term, and search for that.
`tvly search` prints each result's title, full URL and the first 600 characters of its matching passages. Add
`-o .tavily/<name>.json` to also save every result whole, so you can go back to it instead of searching again.
`--max-chars 0` prints the passages whole. Read a promising page in full with `tvly extract <url>`.
**Batch independent searches.** Issue the searches for one step together in one turn, one call each: separate
`tavily_search` calls with MCP tools, or separate Bash calls with the CLI, each holding a single `tvly` command.
MCP calls run in parallel; Bash calls run one after another but still use one turn. Avoid `&`, `$(...)` and
loops, which make the client ask for permission. Put the query in single quotes:
`tvly search 'Rust 2024 edition release date' --depth advanced --max-results 10 -o .tavily/rust-2024.json`.
**Work from saved files.** Keep results in `.tavily/` in the current folder and read them with `head`, `grep` or
`python3`. `-o` creates the folder and keeps it out of git, so don't create it yourself. For example, to find a name or number in a long page:
```bash
tvly extract 'https://example.com/report' -o .tavily/report.json
python3 -c 'import json,re; t=json.load(open(".tavily/report.json"))["results"][0]["raw_content"]; [print(t[max(0,m.start()-200):m.end()+200], "\n---") for m in re.finditer("2019", t)]'
```
Read pages with `tvly extract`, not `curl` or `wget`.
**Ask for 10 results.** Set `max_results` to 10 (`--max-results 10`). **Narrow before you widen.** Filters help more than raising `max_results` further. Use `time_range` or dates for
recent events or a stated period. Use `include_domains` when the answer lives on an official or named site; it
is a hard filter, so search again without it if it doesn't find the page.
**Keep large results on disk.** When a result is long, such as raw page content or a crawl, save it under
`.tavily/` and read only the parts you need. An MCP result lands straight in your context, so keep those calls
small.
**Save copies with `-o`.** Saving results to files is a job for `tvly`: run the call with
`-o .tavily/<name>.json`, even if you searched with MCP tools. A file you write from an MCP result is your
retyping of it, not the original. Without `tvly`, work from the results in your context and don't copy them
into files. If the user asked for a saved copy, give them the URLs and queries, say an exact copy needs the
CLI, and write a retyped copy only if they ask for one.
**Read the results critically.** Count independent sources, not results. Treat a generated answer as a summary
to check, never as a source.
## Extract
Extract returns up to 20 URLs per call as markdown, including pages built with JavaScript.
- Extract only the few results worth reading. Snippets answer most facts.
- Extract full pages by default. Pass `query` (`--query`) only to isolate one fact on a long page; if the passages come
back cut off near what you need, extract again without it.
- Rerun with `extract_depth` set to `advanced` (`--extract-depth advanced`) when a page is built with JavaScript, the content is in a table, or
`basic` came back empty. Check `failed_results` every time and say which pages couldn't be read.
## When to stop
- Stop once two independent sources agree on a fact.
- Before you answer, close any gap your draft would mark unconfirmed or fill from memory: run one targeted
search or reread the saved page.
- For releases, ownership, official figures and decisions by a named body, confirm on the official domain or
repository. A secondary site or a generated answer is not enough.
## Hand off the job
When the user wants an in-depth report that needs many sources gathered and weighed, such as an analysis, a
comparison across several criteria or an in-depth investigation, use `tavily-research` instead of your own searches.
If it isn't installed, run `npx skills add tavily-ai/skills --skill tavily-research` and read its SKILL.md first. A
single fact or answer to find stays here.
© tavily-ai · MIT · tavily-ai/skills
Similar skills
All skills for Agent setup: memory, context, orchestration →tavily-search by other authors comes first.