A high-performance parallel search engine aggregator combining Tavily and Kimi for comprehensive AI-driven research.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install double-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 double-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 Double Search?
The Double Search skill is a powerful tool designed for the Openclaw Skills ecosystem, enabling AI agents to perform simultaneous queries across two premier search engines: Tavily and Kimi. By leveraging asynchronous Python implementation, it provides a broader information net and more accurate data points than single-source searching.
This skill excels at deduplicating results and merging metadata into a unified schema, ensuring that your AI workflows receive the most relevant content without redundant overhead. It is built with fault tolerance in mind, allowing the system to continue functioning even if one search provider experiences downtime.
Double Search Use Cases
- Content creation and deep research requiring multiple perspectives and verified sources.
- Financial analysis where real-time market data and news from different providers must be cross-referenced.
- Technical troubleshooting and code search to aggregate solutions from diverse developer forums and documentation.
- Market intelligence gathering to track trends and competitor movements through high-density web crawling.
How Double Search Works
- The AI agent triggers the search method with a specific query and optional parameters like result limits.
- The skill initiates parallel asynchronous requests to both the Tavily and Kimi APIs using aiohttp.
- Upon receiving responses, the system automatically performs intelligent result merging, ranking, and deduplication.
- A structured JSON payload is returned, containing both a merged list of top results and a source-specific breakdown.
- The AI agent consumes the unified data to generate insights or complete assigned tasks.
Double Search Setup
First, ensure you have the required Python dependencies installed for your Openclaw Skills environment:
pip install aiohttp python-dotenv
Configure your API credentials by creating a .env file or exporting environment variables:
export TAVILY_API_KEY="tvly-xxxxxxxxxxxx"
export KIMI_API_KEY="your_kimi_api_key_here"
Double Search Data Schema & Taxonomy
The skill returns a standardized JSON object containing the following structure:
| Key | Type | Description |
|---|---|---|
query |
string | The original search term used. |
merged_results |
array | A combined list of objects containing title, url, snippet, and source. |
source_breakdown |
object | The raw, unmerged results categorized by tavily and kimi. |
limit_per_source |
integer | The maximum number of results requested from each engine. |
Double Search Advanced Features
- Parallel execution via asyncio to minimize latency and match the speed of the slowest engine.
- Intelligent deduplication and ranking algorithms to prioritize the most relevant information.
- Configurable merge logic allowing users to toggle between a unified list or raw separate source data.
- Built-in error handling to ensure resilient workflows even during partial API failures.
- Support for custom result caching to optimize performance for repetitive queries.
SKILL.md
Loading
Related Openclaw Skills
Singapore Airlines Query Skill
An expert research skill for retrieving structured business intelligence and market performance data for Singapore Airlines.
CN Hot Trends
A unified trend aggregator that fetches real-time hot searches and technical discussions from major Chinese and global platforms.
Chengdu Information Hub
A comprehensive information hub for deep research and business analysis regarding Chengdu entities and industries.
Hangzhou Information Retrieval
A specialized research skill designed to provide structured background information, business maps, and market insights regarding Hangzhou.
ctf-misc
A versatile toolkit for solving complex miscellaneous Capture The Flag (CTF) challenges including jail escapes, esoteric encodings, and system exploitation.
CTF Forensics & Signal Analysis
A comprehensive toolkit for AI agents to perform deep digital forensics, memory analysis, and signal decoding for capture-the-flag competitions.
Featured*
