← 返回 Skills 市场
wetor

123

作者 WéΤοr · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
123
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install baaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
功能描述
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
使用说明 (SKILL.md)

Tavily Search

AI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.

Search

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

Options

  • -n \x3Ccount>: Number of results (default: 5, max: 20)
  • --deep: Use advanced search for deeper research (slower, more comprehensive)
  • --topic \x3Ctopic>: Search topic - general (default) or news
  • --days \x3Cn>: For news topic, limit to last n days

Extract content from URL

node {baseDir}/scripts/extract.mjs "https://example.com/article"

Notes:

  • Needs TAVILY_API_KEY from https://tavily.com
  • Tavily is optimized for AI - returns clean, relevant snippets
  • Use --deep for complex research questions
  • Use --topic news for current events
安全使用建议
This skill's behavior (node scripts that POST queries/URLs to Tavily) is consistent with its description, but there are red flags in the metadata (odd name '123', bizarre registry slug, ownerId mismatch vs _meta.json). Before installing: 1) Verify the publisher and that this is an official Tavily integration (check tavily.com and contact vendor if needed). 2) Do not pass any sensitive queries, secrets, or private URLs to the skill—everything you send is transmitted to an external API. 3) Use a restricted, rotate-able TAVILY_API_KEY with least privilege and monitor its use. 4) If you need stronger assurance, request a trusted release (official package or GitHub release) or ask the publisher to correct metadata inconsistencies. If you cannot verify the publisher, consider the risk of exposing queries and API key and treat the package as untrusted.
能力评估
Purpose & Capability
The skill's declared purpose (Tavily AI-optimized web search) matches the required binary (node), required env var (TAVILY_API_KEY), and the two included scripts which call Tavily's search and extract endpoints. However, registry metadata is inconsistent: top-level skill name is '123', the registry slug is an extremely long garbage string, and _meta.json lists a different ownerId and a sensible slug ('tavily-search'). These inconsistencies could indicate packaging/metadata tampering or republishing under a different registry entry.
Instruction Scope
SKILL.md instructs running the included node scripts with reasonable CLI flags; the scripts only read TAVILY_API_KEY and the provided CLI args, then POST to https://api.tavily.com/search or /extract and print results. Instructions do not read other env vars or local files. Note: any query text or URLs you pass will be transmitted to an external service (Tavily), so do not send sensitive data.
Install Mechanism
There is no install spec (instruction-only with two small node scripts). Nothing is downloaded or extracted by an installer, and the scripts are lightweight and readable.
Credentials
Only a single credential (TAVILY_API_KEY) is required and used directly to authenticate requests to Tavily. That is proportionate to a search/extract integration. Ensure the key has minimal scope and is not shared elsewhere.
Persistence & Privilege
always is false and the skill does not request persistent/privileged system presence. Autonomous invocation (disable-model-invocation false) is the platform default; combined with an external API key this increases blast radius but is expected for an external-search skill.
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 baaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /baaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa 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
11123
元数据
Slug baaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

123 是什么?

AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 123 次。

如何安装 123?

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

123 是免费的吗?

是的,123 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

123 支持哪些平台?

123 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 123?

由 WéΤοr(@wetor)开发并维护,当前版本 v1.0.0。

💬 留言讨论