← 返回 Skills 市场

My Liang Tavily Search

Name: My Liang Tavily Search
Author: ohmaxy

作者 ohMaxy · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

272

总下载

当前安装

版本数

在 OpenClaw 中安装

/install my-liang-tavily-search

功能描述

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

使用说明 (SKILL.md)

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

Option	Description	Default
`-n \x3Ccount>`	Number of results (1-20)	10
`--depth \x3Cmode>`	Search depth: `ultra-fast`, `fast`, `basic`, `advanced`	`basic`
`--topic \x3Ctopic>`	Topic: `general` or `news`	`general`
`--time-range \x3Crange>`	Time range: `day`, `week`, `month`, `year`	-
`--include-domains \x3Cdomains>`	Comma-separated domains to include	-
`--exclude-domains \x3Cdomains>`	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

安全使用建议

This skill appears to do what it claims — it needs Node and your Tavily API key and calls Tavily's official API. Before installing: (1) verify you trust tavily.com and are comfortable sending search queries (and optionally page content) to that service; using --raw-content or similar options may cause more content to be included in API requests, so avoid passing sensitive data; (2) confirm the node runtime on your agent supports global fetch (Node 18+), or run with an appropriate environment; (3) note a minor metadata mismatch (ownerId/version) between the registry listing and _meta.json — if provenance is important, ask the publisher for clarification or inspect the skill source yourself; (4) because the skill can be invoked by the agent, consider limiting when it may run automatically if you have strict data-handling policies.

功能分析

Type: OpenClaw Skill Name: my-liang-tavily-search Version: 1.0.0 The skill is a legitimate implementation of a web search tool using the Tavily API. The script `scripts/search.mjs` safely parses command-line arguments and performs a standard POST request to the official Tavily endpoint (https://api.tavily.com/search) using the provided API key. No malicious behaviors such as data exfiltration, unauthorized execution, or prompt injection were identified.

能力评估

✓ Purpose & Capability

Name/description request Node and a TAVILY_API_KEY and the code performs a POST to https://api.tavily.com/search — these requirements align with a web-search skill that uses Tavily's API.

✓ Instruction Scope

SKILL.md and scripts/search.mjs confine actions to building a search request and calling the Tavily API. The runtime does not read local files, other environment variables, or unrelated system configuration, and it only sends the query and declared options to Tavily.

✓ Install Mechanism

There is no install spec (instruction-only with an included Node script). Nothing is downloaded or written to disk by an installer; the script is run directly with node.

✓ Credentials

Only TAVILY_API_KEY is required and used as the Bearer token for the Tavily API. No additional secrets or unrelated credentials are requested.

✓ Persistence & Privilege

The skill is not configured always:true and does not request system-wide persistence or modification of other skills. Autonomous invocation is allowed by platform default but not elevated by this skill.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install my-liang-tavily-search
安装完成后，直接呼叫该 Skill 的名称或使用 /my-liang-tavily-search 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

- Initial release of Tavily Search skill for web search via Tavily's LLM-optimized API. - Returns relevant web results with content snippets, scores, and metadata. - Script supports search options including result count, depth, topics, time range, domain filters, and output format. - API key authentication via config or environment variable (TAVILY_API_KEY).

元数据

Slug my-liang-tavily-search

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题