A sophisticated headless search and web scraping tool that leverages the Brave Search API to provide structured, markdown-formatted web content.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install brave-headless
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install brave-headless using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is brave-headless?
brave-headless is a powerful CLI tool designed for automated web research and documentation lookup without the overhead of a full browser. By utilizing the Brave Search API, it allows developers to integrate deep web search capabilities directly into their automated workflows. As a core component of the Openclaw Skills ecosystem, it focuses on reliability and performance, featuring built-in fault isolation and parallel fetching to ensure high-quality data retrieval for AI agents and scripts.
This skill is specifically optimized for environments where scriptable, non-interactive web access is required. It bridges the gap between raw search results and usable data by automatically converting complex HTML into clean, readable Markdown, making it an essential asset for developers building search-augmented applications.
brave-headless Use Cases
- Automated web research and documentation lookup for AI coding agents.
- Scriptable URL content extraction for data processing and analysis pipelines.
- Integrating real-time, filtered web search results into command-line applications.
- Gathering clean, Markdown-formatted content from websites for LLM ingestion and context window optimization.
How brave-headless Works
- The user initiates a search query or a specific URL content extraction request via the CLI using a configured Brave Search API key.
- For search queries, the tool retrieves top results from the Brave API and can optionally fetch the full content of those pages in parallel.
- A built-in circuit breaker monitors request health to prevent cascading failures, while an exponential backoff strategy handles transient network errors automatically.
- Extracted HTML content is processed through Readability and Turndown libraries to strip boilerplate and convert the page into structured Markdown.
- The tool applies smart paragraph-boundary truncation to ensure the output fits within defined length limits while maintaining readability.
- The final output is delivered as either human-readable plain text or newline-delimited JSON for seamless integration with other Openclaw Skills.
brave-headless Setup
To get started, navigate to the skill root directory and install the necessary dependencies using npm:
cd <skill-root>
npm ci
You must also configure your Brave Search API key as an environment variable. You can obtain a free key at brave.com/search/api. Set it in your terminal like this:
export BRAVE_API_KEY="your-key-here"
Ensure that you are running Node.js version 20 or higher on a macOS or Linux system to maintain compatibility with these Openclaw Skills.
brave-headless Data Schema & Taxonomy
The brave-headless skill organizes its data output to be highly compatible with both human readers and automated parsers. When utilizing Openclaw Skills for data retrieval, the following schema is applied to the output:
| Field | Description |
|---|---|
| Title | The title of the webpage retrieved from metadata. |
| URL | The direct source link of the search result or extracted page. |
| Snippet | A brief descriptive summary provided by the Brave Search API. |
| Content | The primary body content of the page, formatted in clean Markdown. |
Using the --json flag transforms this data into a structured JSON object per line, ideal for piping into subsequent data processing steps.
brave-headless Advanced Features
- Circuit breaker fault isolation with configurable failure thresholds and reset windows.
- Exponential backoff with full jitter to handle rate limits and transient API errors gracefully.
- Bounded concurrency for parallel page fetching, allowing for fast multi-page data extraction.
- Smart truncation that respects paragraph boundaries to prevent cutting off text mid-sentence.
- Fully validated configuration schema that ensures misconfigured environment variables are caught before execution begins in the Openclaw Skills environment.
SKILL.md
Loading
Related Openclaw Skills
Document Summary
An automated technical analyst that transforms complex text into structured markdown summaries, key points, and risk assessments.
Document Summary
A professional AI-driven skill that converts long technical documents into structured Markdown summaries including key points and risks.
ZeeLin Twitter/X AutoPost
A browser-based automation tool for X (Twitter) that enables automated posting and follower management without requiring an official API key.
Twitter Web AutoPoster
A specialized automation skill that enables AI agents to scrape trends, draft tweets, and publish posts directly to Twitter/X using browser-based interactions.
Agentic Calling Skill
A comprehensive toolkit that enables AI agents to autonomously handle outbound and inbound phone calls using Twilio integration.
Memory System v2.0
A lightweight, file-based memory system that allows AI agents to persist learnings and decisions with sub-20ms search performance.
Featured*
