brave-search-skill

Search the web using Brave Search API for privacy-focused, independent search results with no tracking.

100 stars

Best use case

brave-search-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Search the web using Brave Search API for privacy-focused, independent search results with no tracking.

Teams using brave-search-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/brave-search-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/trohitg/MachinaOS/main/server/skills/web_agent/brave-search-skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/brave-search-skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How brave-search-skill Compares

Feature / Agentbrave-search-skillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Search the web using Brave Search API for privacy-focused, independent search results with no tracking.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Brave Search Skill

Search the web using the Brave Search API. Brave Search is a privacy-focused, independent search engine that does not track users or profile them.

## How It Works

This skill provides instructions and context. To execute searches, connect the **Brave Search** node to the agent's `input-tools` handle.

## brave_search Tool

Search the web and get relevant results from Brave's independent index.

### Schema Fields

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| query | string | Yes | Search query to look up on the web |

### Node Parameters

Additional options configured on the node:

| Parameter | Default | Description |
|-----------|---------|-------------|
| maxResults | 10 | Number of results to return (max 100) |
| country | (empty) | Country code for regional results (e.g., US, GB, DE) |
| searchLang | (empty) | Language code for search results (e.g., en, es, fr) |
| safeSearch | moderate | Safe search filtering: off, moderate, strict |

### Response Format

```json
{
  "query": "artificial intelligence news",
  "results": [
    {
      "title": "AI Breakthrough in Medical Research",
      "snippet": "Researchers have developed a new AI model that can predict...",
      "url": "https://example.com/ai-medical-research"
    }
  ],
  "result_count": 10,
  "provider": "brave_search"
}
```

### Examples

**General search:**
```json
{
  "query": "latest news about artificial intelligence"
}
```

**Technical search:**
```json
{
  "query": "Python asyncio best practices 2026"
}
```

**Local search:**
```json
{
  "query": "best restaurants in San Francisco"
}
```

## When to Use Brave Search

- **Privacy-focused results** - No user tracking or profiling
- **Independent index** - Not reliant on Google or Bing
- **General web search** - News, facts, documentation, products
- **Regional results** - Use country/language parameters for localized results

## When NOT to Use Brave Search

- **AI-powered answers** - Use Perplexity instead for synthesized answers with citations
- **Google-specific results** - Use Serper for Google's index
- **Simple calculations** - Use the calculator tool
- **Creative tasks** - Writing, brainstorming, analysis

## Search Query Best Practices

- Use specific, focused queries (under 10 words when possible)
- Include relevant keywords, dates, and context
- Break complex questions into simpler searches
- Avoid filler words like "please" or "can you tell me"

## API Details

- **API**: GET `https://api.search.brave.com/res/v1/web/search`
- **Auth**: `X-Subscription-Token` header
- **Rate Limits**: Depends on plan (Free: 1 query/sec, 2000/month)
- **Pricing**: ~$0.003 per query

## Setup Requirements

1. Connect this skill to the agent's `input-skill` handle
2. Connect the **Brave Search** node to the agent's `input-tools` handle
3. Add your Brave Search API key in Credentials > Search

Related Skills

serper-search-skill

100
from trohitg/MachinaOS

Search the web using Serper API for Google-powered search results including web, news, images, and places.

perplexity-search-skill

100
from trohitg/MachinaOS

Search the web using Perplexity Sonar AI for synthesized answers with citations, related questions, and optional images.

duckduckgo-search-skill

100
from trohitg/MachinaOS

Search the web using DuckDuckGo for free, privacy-focused results with no API key required.

twitter-search-skill

100
from trohitg/MachinaOS

Search for recent tweets on Twitter/X using keywords, hashtags, mentions, and advanced query operators. Returns rich tweet data with expanded URLs, author info, media, metrics, and referenced tweets.

fs-search-skill

100
from trohitg/MachinaOS

Search the filesystem with ls (list directory), glob (pattern match), or grep (search file contents).

proxy-config-skill

100
from trohitg/MachinaOS

Configure residential proxy providers and make proxied HTTP requests with geo-targeting.

http-request-skill

100
from trohitg/MachinaOS

Make HTTP requests to external APIs and web services. Supports GET, POST, PUT, DELETE, PATCH methods with headers and JSON body.

crawlee-scraper-skill

100
from trohitg/MachinaOS

Read and extract content from any web page URL.

browser-skill

100
from trohitg/MachinaOS

Interactive browser automation - navigate, click, type, fill forms, take screenshots, get accessibility snapshots. Supports system Chrome/Edge via auto-detection.

apify-skill

100
from trohitg/MachinaOS

Run web scrapers and extract data from websites and social media platforms using Apify actors. Supports Instagram, TikTok, Twitter/X, LinkedIn, Facebook, YouTube, Google Search, and general web crawling.

nearby-places-skill

100
from trohitg/MachinaOS

Search for nearby places like restaurants, cafes, stores, and services using Google Places API. Find places by type and location.

shell-skill

100
from trohitg/MachinaOS

Execute short-lived shell commands in a sandboxed environment. No PATH access -- use process_manager for npm/python/node commands.