agiprolabs/claude-trading-skills
67 trading, DeFi, and quantitative finance Agent Skills. Works with Claude Code, Cursor, Codex, Gemini CLI, and 30+ other tools.
What it solves
This project provides a comprehensive library of 67 specialized "Agent Skills" designed to transform AI agents (like Claude Code, Cursor, or Gemini CLI) into professional trading analysts. It eliminates the need for users to manually write API boilerplate for market data, on-chain research, and quantitative analysis, allowing agents to execute complex, multi-step financial workflows.
How it works
The project follows the open Agent Skills standard, providing a set of documented skills (each with a SKILL.md file) that AI agents can automatically discover and use. These skills integrate with various APIs and libraries, such as Birdeye, DexScreener, Helius, and pandas-ta, to perform specific tasks. Users can install these skills via a plugin marketplace or by manually copying the skill files into their agent's designated skills directory.
Who it’s for
It is designed for quantitative traders, DeFi researchers, and crypto analysts who use AI agents to automate market research, backtesting, risk management, and tax compliance.
Highlights
- Broad Market Coverage: Includes 67 skills across 17 categories, including Market Data, Solana Infrastructure, On-Chain Analysis, and Prediction Markets.
- Deep Solana Integration: Specialized tools for PumpFun mechanics, Jito bundles, and Yellowstone gRPC.
- Quant Finance Toolkit: Built-in support for technical analysis (TA-Lib, pandas-ta), backtesting (vectorbt, Backtrader), and statistical methods like regime detection.
- Compliance Tools: Dedicated skills for cost-basis engines, wash-sale detection, and tax-loss harvesting.
- Agent Agnostic: Compatible with 30+ tools including Claude Code, Cursor, Codex, and Gemini CLI.
Related
- Project
- Project
- Project
- Project
- Project