Review generated development artifacts against project plans, especially AI-agent research-run outputs, and write traceable local review reports and fix-plan drafts.
Review quantitative factor redundancy across one or more investment objects without mixing raw observations across objects. Use when cleaning factor sets, classifying duplicate or mirror factors, generating keep/exclude/downweight decisions, or preparing traceable factor-redundancy artifacts before strategy research.
Coding-agent workflow for building and testing Tushare-backed data features in this repository. Use when implementing stock data ingestion, chip distribution analysis, strategy signals, scan APIs, or data exports with the Tushare Python SDK.
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。