skills.rest
moondevonyt
moondevonytCOMMUNITY
Explore all skills by this author →
Website𝕏@MoonDevOnYTGitHub

moon-dev-trading-agents

Organizes expert knowledge of 48+ AI trading agents across multi-exchange workflows.

Updated Aug 23, 2026
Search Tags:#automation#llm#ai agents#risk management#backtesting#multi-exchange#crypto trading
One-click install
npx skills add https://github.com/moondevonyt/moon-dev-ai-agents --skill moon-dev-trading-agents
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: moon-dev-trading-agents
Source: https://github.com/moondevonyt/moon-dev-ai-agents/tree/main/.claude/skills/moon-dev-trading-agents
Command: npx skills add https://github.com/moondevonyt/moon-dev-ai-agents --skill moon-dev-trading-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires backtesting.py, pandas_ta, talib, python-dotenv, termcolor, anthropic, openai, deepseek, groq, google-generativeai, ollama, and includes references (resource) components.

What problem does it solve?

This Skill provides Claude with expert knowledge to navigate and master Moon Dev's extensive AI trading system. It automates complex, data-driven trading decisions and tasks across multiple crypto exchanges, significantly reducing manual effort and complexity for users. By orchestrating specialized AI agents, it helps users research, backtest, and execute trading strategies autonomously, saving time and enhancing decision-making.

Core Features & Use Cases

  • 48+ Specialized AI Agents: Access a comprehensive suite of agents for backtesting, live trading, market analysis, content creation, and more.
  • Multi-Exchange Support: Seamlessly integrate and trade across Hyperliquid, Solana (BirdEye), and Extended Exchange.
  • LLM Abstraction: Dynamically switch between Claude, GPT-4, DeepSeek, Groq, Gemini, and Ollama for optimal AI performance and cost efficiency.
  • Automated Backtesting (RBI Agent): Generate and test trading strategies from YouTube videos, PDFs, or plain text descriptions, turning ideas into actionable code.
  • Use Case: A quant trader can use this Skill to instruct Claude to run the RBI agent, automatically coding and backtesting a strategy from a new research paper. Once validated, Claude can then guide the deployment of the trading_agent with the risk_agent on Hyperliquid, while the sentiment_agent continuously monitors social media for market sentiment.

Quick Start

Guide me on how to activate my Python environment and then run the main orchestrator (src/main.py) to start my AI trading agents.

Frequently Asked Questions about moon-dev-trading-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate crypto trading across multiple exchanges with AI agents?▼

Automate crypto trading by orchestrating 48+ specialized AI agents across Hyperliquid, BirdEye, and Extended Exchange. The Skill configures multi-exchange workflows, handles LLM provider switching, and manages agent interactions to execute trades autonomously based on market data and risk parameters.

Can I backtest trading strategies automatically from research papers or videos?▼

Yes. The RBI agent automatically generates and backtests trading strategies from YouTube videos, PDFs, or plain text descriptions. It turns strategy ideas into executable code and validates performance before live deployment.

How do I switch between different LLM providers like Claude, GPT-4, and DeepSeek?▼

The Skill abstracts LLM switching, letting you dynamically select Claude, GPT-4, DeepSeek, Groq, Gemini, or Ollama. This flexibility optimizes for cost and performance across different agent tasks without reconfiguring workflows.

What's the quickest way to get my AI trading agents running?▼

Activate your Python environment, then run the main orchestrator at `src/main.py` to start the AI trading agent suite. The Skill provides architecture references and environment setup guidance across SKILL.md, AGENTS.md, WORKFLOWS.md, and ARCHITECTURE.md.

Can I use sentiment analysis alongside live trading on Hyperliquid?▼

Yes. Deploy the sentiment agent to monitor social media continuously while the trading and risk agents execute on Hyperliquid. Multiple agents work in parallel within the orchestrated workflow to inform live trading decisions.

What dependencies do I need to run the 48+ AI agents?▼

Required: backtesting.py, pandas_ta, talib, python-dotenv, termcolor, and API clients for Anthropic, OpenAI, DeepSeek, Groq, Google Generative AI, and Ollama. These enable backtesting, technical analysis, and multi-LLM support.

Related Skills

Explore More Finance & Accounting Skills→
different-aidifferent-ai
249

debug prod issues

Diagnose Vercel production issues via live logs, deployments, and Neon Postgres.

Official
Advanced
brainbytes-devbrainbytes-dev
10

live-trading-monitoring

Detect and mitigate drift between backtested expectations and live trading performance.

Community
Advanced
YFOOOOYFOOOO
1

technical-indicators

Compute MA, MACD, RSI, and BOLL indicators from OHLCV DataFrames with pandas and ta-lib.

Community
Advanced
CambixxCambixx

trading-strategies

Build, test, and deploy trading strategies for prediction markets in Python.

Community
Advanced