@matthew77

Tavily Search

Web search using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata.

Current version
v1.0.1
90 3.5万All installs 269

name: tavily-search description: Web search using Tavily's LLM-optimized API. Returns relevant results with content snippets, scores, and metadata. homepage: https://tavily.com metadata: {"openclaw":{"emoji":"🔍","requires":{"bins":["node"],"env":["TAVILY_API_KEY"]},"primaryEnv":"TAVILY_API_KEY"}}

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 news

Examples

# 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.org

Options

OptionDescriptionDefault
-n <count>Number of results (1-20)10
--depth <mode>Search depth: ultra-fast, fast, basic, advancedbasic
--topic <topic>Topic: general or newsgeneral
--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-contentInclude full page contentfalse
--jsonOutput raw JSONfalse

Search Depth

DepthLatencyRelevanceUse Case
ultra-fastLowestLowerReal-time chat, autocomplete
fastLowGoodNeed chunks but latency matters
basicMediumHighGeneral-purpose, balanced
advancedHigherHighestPrecision 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

Security Scan

Status

clean

Open VirusTotal

OpenClaw

gpt-5-mini

clean

OpenClaw analysis

The skill's code, instructions, and required credential (TAVILY_API_KEY) are consistent with a simple Tavily web-search wrapper and do not request unrelated access.

Confidence: high

VirusTotal

Type: OpenClaw Skill Name: liang-tavily-search Version: 1.0.1 The skill bundle provides a wrapper for the Tavily Search API. The `SKILL.md` file contains standard documentation and examples for invoking the `search.mjs` script. The `search.mjs` script correctly parses command-line arguments, retrieves the `TAVILY_API_KEY` from environment variables, constructs a JSON payload, and makes a `fetch` request to `https://api.tavily.com/search`. There is no evidence of malicious intent, such as data exfiltration to unauthorized endpoints, arbitrary code execution via unsanitized input, persistence mechanisms, or prompt injection attempts against the OpenClaw agent. All inputs are treated as data for the API request, preventing command injection.

Metadata

  • Owner: @matthew77
  • Created: 2026/03/02
  • Updated: 2026/03/02
  • Versions: 1
  • Comments: 0
  • Scan checked at: 2026/03/02

Runtime

  • env:TAVILY_API_KEY
Tavily Search | ClawHub CN