OmniSearch is a high-performance web search integration that provides Openclaw Skills with real-time internet access and AI-enhanced research capabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install omnisearch
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 omnisearch 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 OmniSearch?
OmniSearch serves as the essential gateway for an AI agent to access the live internet. It bridges the gap between static training data and the rapidly evolving real world by providing a standardized interface for fetching current events, technical specifications, and factual data. By integrating this tool into your Openclaw Skills workflow, you ensure that your agents never suffer from knowledge cutoff issues.
This skill is designed to be the primary method for information retrieval within the OpenClaw environment. It supports multiple search providers, including Perplexity, Brave, and Kagi, allowing for both raw data extraction and AI-summarized insights. Whether you need to verify a statistic or track the latest market trends, OmniSearch delivers structured, citable results directly to your agent.
OmniSearch Use Cases
- Retrieving current market prices for products, cryptocurrencies, or stocks.
- Fact-checking claims or verifying statistics against live web sources.
- Summarizing recent news developments or tech industry updates.
- Finding specific documentation or product reviews for technical research.
- Locating local businesses, restaurants, or services based on user location.
How OmniSearch Works
- The AI agent identifies a need for external information that exceeds its internal training data.
- The agent executes the omnisearch.sh wrapper script with a specific query and search type (AI or Web).
- The skill communicates with the selected provider, such as Perplexity or Brave, to fetch relevant results.
- The script processes the raw search data into a clean, structured Markdown format.
- The agent synthesizes the findings, providing bulleted summaries and clickable source citations for the user.
OmniSearch Setup
To get started with OmniSearch for your Openclaw Skills, ensure the script has the correct permissions and the environment is properly configured:
# Navigate to the skill directory
cd skills/omnisearch
# Grant execution permissions to the search script
chmod +x ./scripts/omnisearch.sh
# Execute a basic AI-enhanced search query
./scripts/omnisearch.sh ai "latest Openclaw Skills updates"
Note: Ensure that mcporter is installed and your API keys for search providers are configured in your environment variables.
OmniSearch Data Schema & Taxonomy
OmniSearch utilizes a structured communication pattern to ensure reliability across different providers. The output is organized into the following schema:
| Component | Description |
|---|---|
| Summary | A 2-5 bullet point synthesis of the most relevant findings. |
| Citations | A list of 2-6 source URLs formatted as clickable Markdown links. |
| Context | Metadata regarding the time-sensitivity or confidence level of the information. |
| Provider | The specific search engine used, such as Perplexity, Brave, Kagi, Tavily, or Exa. |
OmniSearch Advanced Features
- Multi-provider support allowing seamless switching between AI-enhanced results and raw web data.
- AI-summarization mode which automatically synthesizes complex search results before presenting them to the agent.
- Direct mcporter fallback integration to ensure high availability even if wrapper scripts fail.
- Semantic search capabilities via Exa for high-relevance research and deep-link discovery.
- Automatic query optimization designed to work reliably across different Openclaw Skills implementations.
SKILL.md
Loading
Related Openclaw Skills
Todozi Eisenhower Matrix Skill
An Eisenhower matrix API client and LangChain toolset for prioritizing tasks, goals, and notes within automated workflows.
Safe Web Fetch for Token Optimization
A secure web content retrieval tool that optimizes token usage by 50-80% through intelligent Markdown cleaning and multi-layer security.
Markdown Table to Image
A utility that converts Markdown table syntax into clear, centered, and professionally rendered PNG images.
GitLab CLI (glab)
A comprehensive command-line tool for managing GitLab merge requests, issues, pipelines, and repository configurations.
Claw Permission Firewall
A runtime least-privilege firewall that evaluates AI agent actions to prevent data exfiltration and unauthorized system access.
qmd
A high-speed local search utility combining keyword, vector, and LLM reranking for markdown notes and code.
Featured*
