playbooks

home / skills / openclaw / skills / brave-search

brave-search skill

/skills/steipete/brave-search

This skill helps you perform fast web searches and extract content with Brave Search API to inform documentation and fact-finding.

npx playbooks add skill openclaw/skills --skill brave-search

Review the files below or copy the command above to add this skill to your agents.

Files (6)
SKILL.md
1.2 KB
---
name: brave-search
description: Web 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:

```bash
cd ~/Projects/agent-scripts/skills/brave-search
npm ci
```

Needs env: `BRAVE_API_KEY`.

## Search

```bash
./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

```bash
./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

Overview

This skill provides headless web search and page content extraction using the Brave Search API. It performs lightweight queries and can fetch readable page content as Markdown without launching a browser. Use it to retrieve documentation, facts, or archived web content quickly and programmatically.

How this skill works

The skill sends queries to the Brave Search API and returns ranked results, snippets, titles, and links. An optional content extraction mode fetches a target URL and extracts the main readable content as Markdown. It requires a BRAVE_API_KEY environment variable and runs as a small CLI utility or can be integrated into scripts.

When to use it

  • Look up documentation, API references, or implementation examples.
  • Verify factual claims or find up-to-date web references.
  • Programmatically harvest readable content from a known URL.
  • Automate lightweight web search without a full browser or scraper.
  • Archive or back up search results and extracted page content.

Best practices

  • Set BRAVE_API_KEY in your environment before running the skill.
  • Limit result counts for faster responses and lower API usage (use -n).
  • Use --content only when you need full page text to avoid extra fetch time.
  • Respect site robots and rate limits; avoid high-frequency automated requests.
  • Validate extracted Markdown content for formatting and completeness.

Example use cases

  • Search for function usage examples across documentation and include snippets in a report.
  • Fetch a blog post URL and extract its main article content as Markdown for archiving.
  • Collect a small set of authoritative links and snippets to support a research summary.
  • Build a lightweight tool to check current facts or headlines without browser automation.
  • Integrate into a pipeline that enriches items with searchable web references.

FAQ

What do I need to run this skill?

You need a Brave Search API key set as BRAVE_API_KEY and the skill's dependencies installed. Run the install step once before first use.

How do I get full page content?

Use the content mode or the content extraction command with a specific URL to retrieve readable page content as Markdown.