An intelligent AI research assistant that performs multi-source web searches and generates comprehensive, cited summaries.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install search-agent
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 search-agent 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 Search Agent?
The Search Agent is a sophisticated tool designed for the Openclaw Skills ecosystem to bridge the gap between static AI knowledge and the live web. By combining real-time search capabilities with advanced LLM analysis, it enables users to retrieve accurate, up-to-date information without the need for manual browsing. This skill excels at synthesizing complex data points from various domains, including academic papers, news, and technical documentation, ensuring every answer is grounded in verifiable evidence.
Built to enhance productivity, the Search Agent within Openclaw Skills provides a structured approach to information retrieval. It doesn't just return links; it reads, summarizes, and cross-references content to provide a single, coherent response. This makes it a primary choice for developers and researchers who require high-fidelity data and source transparency in their automated workflows.
Search Agent Use Cases
- Academic & Market Research: Rapidly find scholarly articles or industry trends using Openclaw Skills.
- Technical Troubleshooting: Search code repositories and official documentation for specific implementation examples.
- Fact Verification: Cross-reference claims across multiple authoritative sources to ensure data integrity.
- News Aggregation: Stay informed on breaking developments with automated news monitoring and summarization.
- Product Comparison: Aggregate reviews, pricing, and features from across the web for informed decision-making.
How Search Agent Works
- The user provides a query which the agent parses to identify the optimal search type (General, News, Academic, etc.).
- The skill interfaces with search engine APIs to retrieve the most relevant web results based on Openclaw Skills logic.
- Content fetchers extract the raw text and metadata from the identified web pages.
- An AI analyzer processes the extracted data, identifying key facts and resolving conflicting information.
- The citation manager maps every claim to its original source and assigns a credibility score.
- A structured Markdown response is generated, featuring a summary, key findings, and a list of references.
Search Agent Setup
To integrate this skill into your Openclaw Skills environment, configure the necessary API keys and model parameters in your environment file:
# Required API key for web search access
export SEARCH_API_KEY=your_search_api_key
# Configuration for the AI analysis engine
export AI_MODEL=gpt-4
export MAX_RESULTS=10
export TIMEOUT=30000
Search Agent Data Schema & Taxonomy
The Search Agent organizes its findings into a specific schema to maintain clarity and utility within Openclaw Skills.
| Component | Description |
|---|---|
| Summary | A high-level overview of the answer to the user's query. |
| Key Findings | A bulleted list of specific facts, each including an inline citation number. |
| Sources | A list of URLs with titles and calculated credibility scores. |
| Related Queries | Suggested follow-up questions to help users dive deeper into the topic. |
Search Agent Advanced Features
- Multi-Source Intelligence: Switch between general web, academic, news, code, and image search modes.
- Search Operators: Support for advanced syntax like site:domain.com, filetype:pdf, and exact phrase matching.
- Confidence Scoring: Automatically ranks the reliability of sources to prevent the spread of misinformation.
- Seamless Integration: Works alongside other Openclaw Skills such as code-reviewer and translator for multi-step automated tasks.
SKILL.md
Loading
Related Openclaw Skills
LiteRAG
A local retrieval skill that utilizes SQLite for hybrid vector and keyword search across massive documentation libraries without bloating agent memory.
OpenClaw Agent Log Skill
An automated evidence preservation and trace management skill designed to capture the full lifecycle of OpenClaw agent activities.
Self-Improving Agent
A universal self-improvement system that enables AI agents to learn from every interaction and autonomously evolve their codebase based on real-world experiences.
Broker Weekly Monitor
A professional-grade financial monitoring tool that automates the tracking of US retail brokerages, market-wide trading volumes, and the emerging crypto and prediction market ecosystems.
OSCHINA Technical Publisher
A professional automation tool for drafting, managing, and publishing technical articles on the OSCHINA open-source platform.
Xianyu Service Publisher
A professional framework for listing technical services and second-hand items on Alibaba's Xianyu platform to monetize skills effectively.
Featured*
