MCP HubMCP Hub
返回技能列表

brave-search

steipete
更新于 Today
80 次查看
468
45
468
在 GitHub 上查看
开发api

关于

This skill enables headless web search and content extraction using the Brave Search API, requiring only a BRAVE_API_KEY. It allows developers to perform searches and extract article content directly from the command line without a browser. Use it for straightforward web queries and article scraping, but consider the summarize skill for JavaScript-heavy sites that may block extraction.

快速安装

Claude Code

推荐
插件命令推荐
/plugin add https://github.com/steipete/clawdis
Git 克隆备选方式
git clone https://github.com/steipete/clawdis.git ~/.claude/skills/brave-search

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Brave Search

Headless web search (and lightweight content extraction) using Brave Search API. No browser required.

Search

node {baseDir}/scripts/search.mjs "query"
node {baseDir}/scripts/search.mjs "query" -n 10
node {baseDir}/scripts/search.mjs "query" --content
node {baseDir}/scripts/search.mjs "query" -n 3 --content

Extract a page

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

Notes:

  • Needs BRAVE_API_KEY.
  • Content extraction is best-effort (good for articles; not for app-like sites).
  • If a site is blocked or too JS-heavy, prefer the summarize skill (it can use a Firecrawl fallback).

GitHub 仓库

steipete/clawdis
路径: skills/brave-search
relaywhatsapp

相关推荐技能