← 返回 Skills 市场
OpenClaw Tavily Search (lym)
作者
lym20220107
· GitHub ↗
· v1.0.0
· MIT-0
78
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install lym-tavily-search
功能描述
Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable...
使用说明 (SKILL.md)
Tavily Search
Use the bundled script to search the web with Tavily.
Requirements
- Provide API key via either:
- environment variable:
TAVILY_API_KEY, or ~/.openclaw/.envline:TAVILY_API_KEY=...
- environment variable:
Commands
Run from the OpenClaw workspace:
# raw JSON (default)
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5
# include short answer (if available)
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --include-answer
# stable schema (closer to web_search): {query, results:[{title,url,snippet}], answer?}
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --format brave
# human-readable Markdown list
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --format md
Output
raw (default)
- JSON:
query, optionalanswer,results: [{title,url,content}]
brave
- JSON:
query, optionalanswer,results: [{title,url,snippet}]
md
- A compact Markdown list with title/url/snippet.
Notes
- Keep
max-resultssmall by default (3–5) to reduce token/reading load. - Prefer returning URLs + snippets; fetch full pages only when needed.
安全使用建议
This skill appears to be a simple Tavily search client, but before installing: 1) confirm you are happy giving a Tavily API key (TAVILY_API_KEY) — the registry did not declare this requirement even though the code uses it; 2) verify the publisher and endpoint (https://api.tavily.com/search) are legitimate for your use; 3) inspect any ~/.openclaw/.env file to ensure it doesn't contain unrelated secrets (the script searches that file for TAVILY_API_KEY); 4) note the package metadata (_meta.json) and registry metadata differ (ownerId/version), which may indicate sloppy packaging — consider asking the publisher to reconcile metadata or provide a signed/verified release before trusting with sensitive credentials.
功能分析
Type: OpenClaw Skill
Name: lym-tavily-search
Version: 1.0.0
The skill bundle provides a standard implementation for performing web searches via the Tavily API. The Python script (scripts/tavily_search.py) uses the standard library to communicate with the official Tavily endpoint and correctly handles API key retrieval from environment variables or a local configuration file as described in SKILL.md.
能力评估
Purpose & Capability
Functionality (web search via Tavily) matches the name and included script: the script POSTS queries to https://api.tavily.com/search. However the registry metadata lists no required env vars while the runtime requires TAVILY_API_KEY, an inconsistency that should have been declared.
Instruction Scope
SKILL.md and the script keep scope to searching Tavily and formatting results. The only additional access is reading TAVILY_API_KEY from the environment or ~/.openclaw/.env as documented in SKILL.md.
Install Mechanism
No install spec; this is an instruction-only skill with a small Python script. Nothing is downloaded or written by an installer.
Credentials
The script legitimately needs a single API key (TAVILY_API_KEY). But the skill registry metadata does not declare this required env var or a primary credential; additionally the script will read ~/.openclaw/.env which may contain other secrets—this file path was not declared in the manifest.
Persistence & Privilege
always is false and there are no actions that modify other skills or system-wide settings. The skill does not request elevated persistence.
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 lym-tavily-search - 安装完成后,直接呼叫该 Skill 的名称或使用
/lym-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: web search via Tavily API for OpenClaw agents
元数据
常见问题
OpenClaw Tavily Search (lym) 是什么?
Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 78 次。
如何安装 OpenClaw Tavily Search (lym)?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install lym-tavily-search」即可一键安装,无需额外配置。
OpenClaw Tavily Search (lym) 是免费的吗?
是的,OpenClaw Tavily Search (lym) 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
OpenClaw Tavily Search (lym) 支持哪些平台?
OpenClaw Tavily Search (lym) 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 OpenClaw Tavily Search (lym)?
由 lym20220107(@lym20220107)开发并维护,当前版本 v1.0.0。
推荐 Skills