brave-search

Nsttt's avatarfrom Nsttt

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 9, 2026
[Web Research]

When & Why to Use This Skill

The Brave Search skill enables Claude to perform high-performance web searching and markdown content extraction using the Brave Search API. It provides a lightweight, browser-less solution for agents to access real-time information, technical documentation, and specific web data, significantly enhancing the accuracy and depth of AI-generated insights.

Use Cases

  • Technical Documentation Retrieval: Quickly locate and extract specific API references, library documentation, or coding tutorials to assist in software development and debugging.
  • Real-time Fact-Checking: Verify claims and look up current events, statistics, or news that occurred after the model's last training data cutoff.
  • Clean Content Extraction: Fetch specific URLs and convert web page content into clean markdown for easier summarization, data analysis, or knowledge base integration.
  • Automated Market Intelligence: Conduct broad web searches to monitor industry trends, competitor updates, and public sentiment without the need for manual browsing.
namebrave-search
descriptionWeb search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

Brave Search

Headless web search and content extraction using Brave Search. No browser required.

Setup

Run once before first use:

cd ~/git/agents/skills/brave-search
npm ci

Needs env: BRAVE_API_KEY.

Search

./search.js "query"                    # Basic search (5 results)
./search.js "query" -n 10              # More results
./search.js "query" --content          # Include page content as markdown
./search.js "query" -n 3 --content     # Combined

Extract Page Content

./content.js https://example.com/article

Fetches a URL and extracts readable content as markdown.

Output Format

--- Result 1 ---
Title: Page Title
Link: https://example.com/page
Snippet: Description from search results
Content: (if --content flag used)
  Markdown content extracted from the page...

--- Result 2 ---
...

When to Use

  • Searching for documentation or API references
  • Looking up facts or current information
  • Fetching content from specific URLs
  • Any task requiring web search without interactive browsing