Claude Skill
ALAGENT-HKU/x2strategy
x2strategy is an open-source Claude Skill that extracts structured strategy specifications from quantitative finance research papers, enabling AI agents to parse and standardize trading strategies.
Overview
Repository
Install this Skill
npx clawhub@latest install x2strategyRegistry
npx clawhub@latest install x2strategygit clone https://github.com/ALAGENT-HKU/x2strategy.git ~/.copilot/skills/x2strategygit clone https://github.com/ALAGENT-HKU/x2strategy.git ~/.claude/skills/x2strategygit clone https://github.com/ALAGENT-HKU/x2strategy.git .github/skills/x2strategypip install -e ".[codegen,agent,docx,dev]"
Summary
x2strategy is an open-source Claude Skill designed to extract structured strategy specifications from quantitative finance research papers. It enables AI agents like GitHub Copilot and Claude Code to parse academic papers and output standardized trading strategy definitions, bridging the gap between financial research and algorithmic implementation.
从量化金融研究论文中提取结构化策略规范——适用于 GitHub Copilot 与 Claude Code 的 Agent Skill（Claude Skill）
Key features
- Extracts structured strategy specs from quantitative finance papers
- Outputs standardized trading strategy definitions
- Integrates with GitHub Copilot and Claude Code as an Agent Skill
- Built with Python for efficient paper parsing
- Open-source and community-driven development
Use cases
- Automating strategy extraction from research papers for backtesting
- Enabling AI agents to read and interpret financial literature
- Standardizing trading strategies for cross-platform deployment
- Accelerating quant research workflow with structured outputs
README excerpt
<div align="center"> <img src="assets/alagent_logo.png" alt="ALAGENT Logo" width="120"> # X2Strategy **Any Research Input → Strategy Spec → Executable Code → Backtest → Diagnosis** [](https://python.org) [](LICENSE) [](https://agentskills.io/) []() [](https://docs.litellm.ai/docs/providers) [Getting Started](#-getting-started) · [How It Works](#-how-it-works) · [Examples](#-examples) · [Docs](#-documentation) · [简体中文](README_CN.md) --- *Turn quantitative finance research — papers, drafts, reports, or strategy ideas — into validated, executable trading strategies. Automatically.* </div> ## Highlights - **🔬 Multi-Format Input** — PDF papers, Markdown drafts, DOCX reports, plain text. Auto-detected. - **🧠 5-Layer LLM Extraction** — Multi-strategy detection → indicators → signal logic → execution plan → risk controls. - **🧾 Grounded Extraction Quality** — Optional instruction/customization/clarification context, retrieved repair-time operator-pitfall checks, canonical `portfolio_weights`, and structured `needs_human_review` flags. - **✅ Verified Code Generation** — AST validation + Backtrader structural checks + indicator registry, not just "generate and hope". - **📊 Automated Backtesting** — Execute, extract metrics, and diagnose against paper-reported performance. - **🤖 Agent-Native** — Works as an [Agent Skill](https://agentskills.io/) (`/x2strategy
Topics
No topics yet.