A secure local browser automation tool for searching and extracting web content across multiple engines without the need for API keys.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browser-search
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 browser-search 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 Browser Search?
The Browser Search tool is a specialized capability within the Openclaw Skills ecosystem that allows AI agents to perform automated web searches using a local Chromium browser. It is designed to bridge the gap between AI reasoning and real-time web data by interacting directly with search engines like Bing, Google, Baidu, and DuckDuckGo.
This skill prioritizes security and privacy by running entirely on the local machine. It avoids the complexities of third-party API configurations and ensures that all data extraction remains within user-defined boundaries, making it an essential tool for developers building localized and secure research agents.
Browser Search Use Cases
- Tracking real-time news updates and global trends without manual browsing.
- Gathering technical documentation, library references, and coding tutorials from multiple search providers.
- Conducting competitive market research using publicly available search engine data.
- Automating the collection of search result metadata for data analysis pipelines.
How Browser Search Works
- The AI agent identifies a search-related prompt and activates the browser-search tool.
- The skill launches a local Chromium instance to navigate to the chosen search engine (defaulting to Google or specified engine).
- It executes the query and monitors the page load while strictly adhering to internal safety timeouts.
- The tool extracts relevant data fields, including titles, links, and summaries, from the search results page.
- Results are formatted into JSON, Markdown, or Plain Text and saved to a secure path in the user's home directory.
Browser Search Setup
To use this feature in your Openclaw Skills environment, ensure you have a Chromium-based browser installed locally. No additional API keys are required.
# Perform a basic search
browser-search "Artificial Intelligence 2026"
# Perform a search using a specific engine
browser-search "AI trends" --engine bing
# Save search results to a specific file with a result limit
browser-search "Python tutorials" --output ~/results.json --max 5
Browser Search Data Schema & Taxonomy
The skill organizes extracted web data into a clean structure. Note that for security, all output paths must reside within the user home directory.
| Field | Description | Data Type |
|---|---|---|
| Title | The display title of the search result | String |
| Link | The destination URL for the result | URL |
| Snippet | A brief summary or excerpt from the page | String |
| Engine | The search engine used for the query | Enum |
| Timestamp | The exact time the search was conducted | ISO8601 |
Browser Search Advanced Features
- Support for multiple search engines including regional favorites like Baidu and privacy-focused DuckDuckGo.
- Secure execution environment that prohibits dangerous functions like eval or exec to protect the local system.
- Strict file path enforcement that prevents the AI agent from writing data to sensitive system directories.
- Automated content extraction optimized for Openclaw Skills, providing clean summaries rather than raw HTML.
- Seamless integration with multi-agent workflows for complex research and reporting tasks.
SKILL.md
Loading
Related Openclaw Skills
Agent Directory
A specialized registry and discovery engine for AI agents to find services, infrastructure, and standardized skill definitions.
News Summary
A local automation utility for parsing RSS feeds and generating concise news title summaries.
Story Biographer
A specialized writing skill that transforms oral history transcripts and life reviews into structured, voice-preserving narrative biographies.
Mio-Companion
Mio-Companion is a proactive AI agent skill designed to learn user habits, initiate meaningful conversations, and automatically manage schedules based on task extraction.
OctenSearch
OctenSearch is a high-performance web search skill providing AI agents with real-time, LLM-optimized data in under 80ms.
Playwright Browser Automation
A high-performance browser automation skill that enables fast, reliable, and modern web scraping and testing across multiple browser engines.
Featured*
