Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

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.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add tavily-ai/skills --skill tavily-search -a claude-code
Open on GitHub

What 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-code

2Manually: put the files in place

~/.claude/skills/tavily-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tavily-search/

From the same set6

The whole set →

Similar

resume-quantifier Paramchoudhary A skill that spots resume bullets without numbers and helps estimate metrics when exact data is missing. Useful when your experience section has no quantifiable results. Claude Code CX Codex Cursor +1 10,000installs android-emulator callstack This skill drives an Android Emulator with agent-device: it launches apps, checks live UI, and gathers debugging evidence. It fits native, React Native, Expo, and Flutter apps. Claude Code CX Codex Cursor +1 4,600installs codex Hermes Agent This skill delegates coding tasks to OpenAI's Codex agent via CLI. Use it to automate features, refactoring, PR reviews, and batch issue fixes directly from the terminal. Claude Code CX Codex Cursor +1 414installs resume-section-builder Paramchoudhary A skill that generates resume sections tailored to experience level and role. Builds professional summaries, organizes skills, formats work history and education with different rules for entry level, mid-career and senior. Claude Code CX Codex Cursor +1 9,800installs inspector-docs CopilotKit Keeps CopilotKit documentation aligned with shipped Inspector overlay panes. Use it when adding, editing, or deleting tabs in @copilotkit/web-inspector. Claude Code CX Codex Cursor +1 1,000installs native-sdk vercel-labs Teaches coding agents to scaffold and build native desktop apps using Native SDK. Recommended when writing declarative .native markup and AOT-compiled TypeScript. Claude Code CX Codex Cursor +1 1,500installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. Claude Code 711,230installs

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

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor