Route prompts to JoinQuant API categories and templates for runnable strategy code.
npx skills add https://github.com/gaaiyun/joinquant-skill --skill joinquant-skill
Please help me install this Agent Skill. Skill: joinquant-skill Source: https://github.com/gaaiyun/joinquant-skill/tree/main Command: npx skills add https://github.com/gaaiyun/joinquant-skill --skill joinquant-skill
AI agents often struggle to generate correct, runnable code for the JoinQuant platform. This Skill provides a structured API knowledge base, production-ready templates, static linting, factor libraries, and a research-to-strategy pipeline to ensure accurate results and smooth integration.
Use a natural-language request like: "Write a mean‑reversion strategy for the Shanghai market using RSI and Bollinger bands and paste it into JoinQuant editor."
High-intent search queries and answers about installing and using this skill.
To generate runnable JoinQuant strategies from AI prompts, route natural language requests through 14 API categories and 5 production-ready templates to output executable stock, ETF, and futures code.
Preventing hallucinated APIs in JoinQuant code generation requires a local lint tool that catches invalid functions, future-function violations, and missing price-mode, slippage, or commission settings before execution.
You can use broker research reports to build JoinQuant-compatible trading strategies by utilizing a research importer pipeline that translates report logic into executable factor library code.
The JoinQuant skill includes 5 production-ready templates for ETF rotation, mean-reversion, momentum, multi-factor, and basic strategies, each with embedded rationale and guardrails for immediate deployment.
Perform single-factor analysis for local model evaluation in JoinQuant by utilizing the integrated factor library tools, which support local research and assess factor efficacy before strategy integration.
AI generated trading strategies fail JoinQuant platform lint checks due to missing slippage or commission configurations, future-function violations, or referencing hallucinated APIs not present in the 14 supported categories.
digital-stoic-orgAutomate monorepo-aware dependency installation across Python, JavaScript, and system packages.
ThanhNguyenDatConstruct financial backtesting systems with event-driven simulation and walk-forward optimization.
NigarumOvumEvaluate financial cross-sectional factor libraries with Python and HTML reporting.
20YN04Translate Vibe-Trading backtest strategies into executable vnpy CtaTemplate Python classes.
