Tavily Search
- 649 installs
- skills.volces.com
Tavily Search is an agent skill that performs web searches optimized for LLMs and returns concise, cited results to ground AI responses in real data.
About
Tavily Search is an agent skill that connects your AI coding assistant to a search engine purpose-built for LLMs. Instead of relying on stale training data or fabricating answers, your agent can issue precise queries and receive clean, summarized results with citations. Builders use it whenever their agent needs current information, market data, API documentation, competitor details, or technical references. It turns generic chat-based coding into a grounded research partner that can pull live context on demand. The skill is lightweight, fast, and designed specifically for agentic workflows where accuracy and freshness matter.
- Performs targeted web searches optimized for AI agents and LLMs
- Returns concise, relevant results with source citations
- Reduces hallucinations by grounding responses in fresh web data
- Seamless integration with Claude Code, Cursor, and other agents
- 631 developers have installed this skill
Tavily Search by the numbers
- 649 all-time installs (skills.sh)
- +1 installs in the week ending Jul 27, 2026 (Skillselion tracking)
- Ranked #1,488 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 27, 2026 (Skillselion catalog sync)
npx skills add https://github.com/skills.volces.com --skill tavily-searchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 649 |
|---|---|
| Repository | skills.volces.com ↗ |
What it does
Give their coding agent high-quality, real-time web search results instead of hallucinated answers.
Who is it for?
Best when you use Claude, Cursor, or similar agents and frequently need fresh web context during research, planning, or implementation.
Skip if: Skip if you're working entirely offline or on fully internal codebases with no need for external information.
When should I use this skill?
When your agent needs current information from the web or when you want to reduce hallucinations by grounding responses with real search results.
What you get
Your agent receives accurate, up-to-date search results that reduce hallucinations and improve the quality of generated code, plans, and decisions.
- Search results with sources and citations returned to the calling agent
By the numbers
- 631 installs
Files
Tavily Search
Search the web and get relevant results optimized for LLM consumption.
Authentication
Get your API key at https://tavily.com and add to your OpenClaw config:
{
"skills": {
"entries": {
"tavily-search": {
"enabled": true,
"apiKey": "tvly-YOUR_API_KEY_HERE"
}
}
}
}Or set the environment variable:
export TAVILY_API_KEY="tvly-YOUR_API_KEY_HERE"Quick Start
Using the Script
node {baseDir}/scripts/search.mjs "query"
node {baseDir}/scripts/search.mjs "query" -n 10
node {baseDir}/scripts/search.mjs "query" --deep
node {baseDir}/scripts/search.mjs "query" --topic newsExamples
# Basic search
node {baseDir}/scripts/search.mjs "python async patterns"
# With more results
node {baseDir}/scripts/search.mjs "React hooks tutorial" -n 10
# Advanced search
node {baseDir}/scripts/search.mjs "machine learning" --deep
# News search
node {baseDir}/scripts/search.mjs "AI news" --topic news
# Domain-filtered search
node {baseDir}/scripts/search.mjs "Python docs" --include-domains docs.python.orgOptions
| Option | Description | Default |
|---|---|---|
-n <count> | Number of results (1-20) | 10 |
--depth <mode> | Search depth: ultra-fast, fast, basic, advanced | basic |
--topic <topic> | Topic: general or news | general |
--time-range <range> | Time range: day, week, month, year | - |
--include-domains <domains> | Comma-separated domains to include | - |
--exclude-domains <domains> | Comma-separated domains to exclude | - |
--raw-content | Include full page content | false |
--json | Output raw JSON | false |
Search Depth
| Depth | Latency | Relevance | Use Case |
|---|---|---|---|
ultra-fast | Lowest | Lower | Real-time chat, autocomplete |
fast | Low | Good | Need chunks but latency matters |
basic | Medium | High | General-purpose, balanced |
advanced | Higher | Highest | Precision matters, research |
Tips
- Keep queries under 400 characters - Think search query, not prompt
- Break complex queries into sub-queries - Better results than one massive query
- Use `--include-domains` to focus on trusted sources
- Use `--time-range` for recent information
- Filter by `score` (0-1) to get highest relevance results
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Use instead of generic web search MCP servers when you need LLM-optimized, concise results with citations.
FAQ
Who is tavily-search for?
Developers who use Claude Code, Cursor, or other AI coding agents and want their agents to retrieve accurate, current information from the web instead of guessing.
When should I use tavily-search?
Use it when your agent needs current API documentation, competitor analysis, latest framework updates, market research, or any live information that its training data cannot provide. It is especially valuable at the start of new projects, during feature scoping, or when validatin
Is tavily-search safe to install?
Yes. Like any skill that makes network calls, users should review the Security Audits panel on this page before installing.