tavily-search · tavily-ai, core — скилл для Claude Code: что делает и как установить
Скилл tavily-search для Claude Code, который подключает поиск по интернету и извлечение данных с веб-страниц. Используется для проверки фактов, чтения актуальных новостей и сбора информации вне обучающей выборки.
MIT 39 400 установок ★ 497 обновлён 2026-10-23
npx skills add tavily-ai/skills --skill tavily-search -a claude-codeЧто делает tavily-search
Скилл добавляет инструменты для работы с веб-контентом: tavily_search, tavily_extract, tavily_map и tavily_crawl. Он позволяет агенту искать информацию, извлекать текст со страниц или обходить разделы сайтов. Если инструменты доступны через MCP, используйте их напрямую, в противном случае работайте через CLI-команду tvly.
Для работы сохраняйте результаты в папку .tavily/ с помощью флага -o, чтобы не перегружать контекст и иметь возможность повторного чтения файлов. Скилл требует, чтобы вы формулировали запросы как для поисковой системы, разделяя сложные вопросы на части. При работе с JavaScript-сайтами или таблицами используйте extract_depth со значением advanced.
Какие задачи решает
- Проверить актуальные факты или новости
- Извлечь контент с конкретного URL
- Собрать данные со всех страниц раздела сайта
- Уточнить информацию, которой нет в обучающих данных модели
Примеры запросов агенту
- tvly search 'текущая версия Rust' --depth
advanced --max-results 5 tvly extract 'https://example.com/report' -o .tavily/report.json
Как установить tavily-search
1Через Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a claude-code2Вручную: положить файлы
~/.claude/skills/tavily-search/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/tavily-search/
1Через Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a codex2Вручную: положить файлы
.agents/skills/tavily-search/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a cursor2Вручную: положить файлы
.cursor/skills/tavily-search/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install tavily-ai/skills skills/core/tavily-search2Вручную: положить файлы
.github/skills/tavily-search/SKILL.md1Через Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a gemini-cli2Командой платформы
gemini skills install https://github.com/tavily-ai/skills --path skills/core/tavily-searchВручную: положить файлы
.devin/skills/tavily-search/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add tavily-ai/skills --skill tavily-search -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о tavily-search
Как установить tavily-search в Claude Code?
Выполните команду npx skills add tavily-ai/skills --skill tavily-search -a claude-code в терминале вашего проекта.
Что делает tavily-search?
Он позволяет агенту искать в интернете, читать URL и извлекать данные, когда собственных знаний модели недостаточно.
Что нужно для работы tavily-search?
Скилл использует инструменты tvly CLI или MCP, которые должны быть доступны в среде выполнения.
Исходный текст
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
Похожие скиллы
Все скиллы по теме «Настройка агента: память, контекст, субагенты» →Сначала — tavily-search от других авторов.