robonet-workbench
Use Robonet's MCP server to build, backtest, optimize, and deploy trading strategies. Provides 24 specialized tools for crypto and prediction market trading: (1) Data tools for browsing strategies, symbols, indicators, Allora topics, and backtest results, (2) AI tools for generating strategy ideas and code, optimizing parameters, and enhancing with ML predictions, (3) Backtesting tools for testing strategy performance on historical data, (4) Prediction market tools for Polymarket trading strategies, (5) Deployment tools for live trading on Hyperliquid, (6) Account tools for credit management. Use when: building trading strategies, backtesting strategies, deploying trading bots, working with Hyperliquid or Polymarket, or enhancing strategies with Allora Network ML predictions.
Why use this skill?
Build, backtest, and deploy trading strategies on Hyperliquid and Polymarket using AI-powered tools, Allora Network ML predictions, and automated workflows.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/nickemmons/robonet-workbenchWhat This Skill Does
The robonet-workbench skill serves as a comprehensive MCP server integration for building, testing, and deploying high-performance trading strategies. It provides a robust suite of 24 tools designed to bridge the gap between AI-driven idea generation and live market execution. The system covers the entire algorithmic trading lifecycle, including access to market data (Hyperliquid symbols and 170+ technical indicators), AI-assisted strategy code generation, rigorous historical backtesting, and specialized integration with the Allora Network for ML-based price predictions. It is the premier tool for users looking to manage crypto portfolios on Hyperliquid or navigate prediction markets on Polymarket.
Installation
To install this skill, run the following command in your terminal:
clawhub install openclaw/skills/skills/nickemmons/robonet-workbench
Use Cases
- Automated Trading: Develop, backtest, and deploy crypto trading bots on Hyperliquid without writing manual boilerplate code.
- Market Research: Utilize the
get_all_technical_indicatorsandget_all_symbolstools to perform deep-dive analysis on market conditions. - AI-Enhanced Strategies: Integrate Allora Network ML forecasts directly into your Python strategies to gain a predictive edge in volatile markets.
- Prediction Markets: Programmatically build and test YES/NO market strategies for Polymarket, allowing for systematic event-based trading.
Example Prompts
- "Check the current availability of BTC-USDT data, then generate a mean-reversion strategy using RSI and MACD indicators for Hyperliquid."
- "Optimize the parameters for my 'trend-follower-v2' strategy and run a backtest covering the last 6 months of data."
- "Create a new prediction market strategy for the upcoming election outcome on Polymarket and enhance it with current Allora Network ML signals."
Tips & Limitations
- Cost Awareness: AI-Powered strategy tools are the most resource-intensive; utilize the Data Access tools first to confirm your inputs, as these are significantly cheaper.
- Validation: Never deploy a strategy without running
run_backtest. Ensure you test against multiple timeframes to avoid overfitting. - Execution Speed: Most data queries return in under 1 second, whereas strategy generation and backtesting can take up to 60 seconds. Plan your interaction flow accordingly.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-nickemmons-robonet-workbench": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api, code-execution