← 返回 Skills 市场
bert-builder

Tavily AI Search

作者 bert-builder · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
42403
总下载
36
收藏
617
当前安装
1
版本数
在 OpenClaw 中安装
/install tavily
功能描述
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.
安全使用建议
Install only if you are comfortable sending search queries to Tavily under your API key. Prefer TAVILY_API_KEY or a secure config store, avoid putting keys directly on shared command lines, pin or review tavily-python before use in sensitive environments, and treat search results or curled pages as untrusted until verified.
功能分析
Type: OpenClaw Skill Name: tavily Version: 1.0.0 The skill bundle provides a Python script for interacting with the Tavily search API, which appears benign and correctly handles API keys. However, the `SKILL.md` documentation includes an 'Integration Patterns' example demonstrating how to chain the search results with `jq` and `curl` to fetch raw content from URLs (`scripts/tavily_search.py "React documentation" --json | jq -r '.results[].url' | xargs -I {} curl -s {}`). While presented as a legitimate content extraction method, this example highlights the agent's capability to execute arbitrary network requests (`curl`) based on search results, which is a high-risk primitive that could be exploited by a malicious prompt to access or exfiltrate data from unintended external or internal network resources. This capability, though not explicitly malicious in its stated purpose, makes the skill suspicious due to the potential for misuse via prompt injection.
能力评估
Purpose & Capability
The SKILL.md, reference doc, and Python script consistently implement Tavily search, domain filtering, AI answers, images, and optional raw content retrieval.
Instruction Scope
The instructions are user-directed and non-destructive, but they include a shell pipeline that curls search-result URLs; that is purpose-aligned content extraction, though users should avoid blindly fetching untrusted results.
Install Mechanism
The skill has no automatic installer and tells users to manually install the unpinned tavily-python package, so dependency provenance and versioning remain the user's responsibility.
Credentials
A Tavily API key is expected and documented, and the script reads only --api-key or TAVILY_API_KEY; the frontmatter does not formally declare the required credential.
Persistence & Privilege
The artifacts show no background workers, persistence, privilege escalation, protected-path writes, local credential-store access, deletion, or destructive behavior.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install tavily
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /tavily 触发
  4. 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: AI-optimized web search with basic/advanced modes, domain filtering, news search, image search, and AI answer generation.
元数据
Slug tavily
版本 1.0.0
许可证
累计安装 1761
当前安装数 617
历史版本数 1
常见问题

Tavily AI Search 是什么?

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 42403 次。

如何安装 Tavily AI Search?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install tavily」即可一键安装,无需额外配置。

Tavily AI Search 是免费的吗?

是的,Tavily AI Search 完全免费(开源免费),可自由下载、安装和使用。

Tavily AI Search 支持哪些平台?

Tavily AI Search 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 Tavily AI Search?

由 bert-builder(@bert-builder)开发并维护,当前版本 v1.0.0。

💬 留言讨论