tavily-search — Claude Code skill: what it does, how to install
Runs web searches via the tvly CLI and returns LLM-tailored snippets with relevance scores. Use it when your agent needs fresh web sources without an exact URL.
npx skills add tavily-ai/skills --skill tavily-search -a claude-codeWhat tavily-search does
This skill executes the tvly search command via Bash. By default, it returns up to 5 results with relevance scores and metadata. You can tune search depth with the --depth flag from ultra-fast to advanced. Search prompts work best under 400 characters, so complex questions should be split into smaller sub-queries.
Before running, make sure the tvly CLI is installed on your machine. You do not need an API key right away because search supports capped keyless access. If an interactive session hits that cap, run tvly login once to authenticate through your browser; in unattended environments, the skill reports the cap instead of blocking.
Filters handle domain whitelisting, time ranges, and content extraction. Passing --include-raw-content returns full page text right inside the search response. That eliminates a separate extraction step.
What it helps with
- retrieve recent news articles bounded by specific timeframes
- filter web search results by trusted domain lists
- pull raw web page text directly into the agent context
- search factual information with source relevance scores
Example prompts for the agent
- Search for recent AI news published in the past week
- Find SEC filings for Apple on sec.gov
- Look up a React hooks tutorial and include raw page content
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 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/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
From the same set6
The whole set →Similar
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 terminal.
What does tavily-search do?
It performs web searches through the Tavily CLI and formats results with relevance scores, summaries, and optional full text for language models.
Do I need a Tavily API key to use this skill?
You can start without an API key because the search CLI offers a capped keyless tier. Once you hit the limit, authenticate by running tvly login.
Source text
SKILL.md · MIT
--- name: tavily-search description: | Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths. allowed-tools: Bash(tvly *) --- # tavily search Web search returning LLM-optimized results with content snippets and relevance scores. ## Before running Run search directly when `tvly` is available. Search supports capped keyless access, so do not look for an API key or authenticate before the first request. If `tvly` is missing, follow the [tavily-cli setup](../tavily-cli/SKILL.md#setup) before retrying. If the keyless cap is reached in an interactive session, run `tvly login` to open browser OAuth, then retry the original search once. In an unattended environment, report the cap and authentication options instead of starting an interactive flow. Do not start a second login immediately after guided setup has completed. ## When to use - You need to find information on any topic - You don't have a specific URL yet - First step in the [workflow](../tavily-cli/SKILL.md): **search** → extract → map → crawl → research ## Quick start ```bash # Basic search tvly search "your query" --json # Advanced search with more results tvly search "quantum computing" --depth advanced --max-results 10 --json # Recent news tvly search "AI news" --time-range week --topic news --json # Domain-filtered tvly search "SEC filings" --include-domains sec.gov,reuters.com --json # Include full page content in results tvly search "react hooks tutorial" --include-raw-content --max-results 3 --json ``` ## Options | Option | Description | |--------|-------------| | `--depth` | `ultra-fast`, `fast`, `basic` (default), `advanced` | | `--max-results` | Max results, 0-20 (default: 5) | | `--topic` | `general` (default), `news`, `finance` | | `--time-range` | `day`, `week`, `month`, `year` | | `--start-date` | Results after date (YYYY-MM-DD) | | `--end-date` | Results before date (YYYY-MM-DD) | | `--include-domains` | Comma-separated domains to include | | `--exclude-domains` | Comma-separated domains to exclude | | `--country` | Boost results from country | | `--include-answer` | Include AI answer (`basic` or `advanced`) | | `--include-raw-content` | Include full page content (`markdown` or `text`) | | `--include-images` | Include image results | | `--include-image-descriptions` | Include AI image descriptions | | `--chunks-per-source` | Chunks per source (advanced/fast depth only) | | `-o, --output` | Save the JSON response to a file | | `--json` | Structured JSON output | ## Search depth | Depth | Speed | Relevance | Best for | |-------|-------|-----------|----------| | `ultra-fast` | Fastest | Lower | Real-time chat, autocomplete | | `fast` | Fast | Good | Need chunks, latency matters | | `basic` | Medium | High | General-purpose (default) | | `advanced` | Slower | Highest | Precision, specific facts | ## Tips - **Keep queries under 400 characters** — think search query, not prompt. - **Break complex queries into sub-queries** for better results. - **Use `--include-raw-content`** when you need full page text (saves a separate extract call). - **Use `--include-domains`** to focus on trusted sources. - **Use `--time-range`** for recent information. - **Verify identity-sensitive facts at the exact primary source.** For releases, versions, ownership, or similarly named projects, confirm the official repository or domain instead of trusting a generated answer or package-name match alone. - Read from stdin: `echo "query" | tvly search - --json` ## See also - [tavily-extract](../tavily-extract/SKILL.md) — extract content from specific URLs - [tavily-research](../tavily-research/SKILL.md) — comprehensive multi-source research
© tavily-ai · MIT · tavily-ai/skills