Explain, implement, or debug TqSdk Python workflows for waitupdate or ischanging update loops, market data retrieval, historical download, account type selection, funds or positions or orders or trades, field meanings, order placement or cancellation, target-position tools, TqScenario margin trials, real-account…
Find and read papers from local markdown/wiki corpus. Disambiguate ambiguous queries, search by keyword + abstract + full-text, judge by author-graded rubric, and read with L1/L2/L3 strategy. Use when: find papers in local corpus, search wiki, read a local report, keyword search across extracted knowledge. Do NOT use…
Use this skill to map the genealogical lineage and historical progression of a research field. It is designed to visualize the evolutionary path of ideas, showing how technical challenges in earlier works were addressed by subsequent research improvements. The final deliverable is a Markdown file with embedded Mermaid…
A procedure for turning a trading strategy or research report into a QMT daily factor backtest script. QMT is a Chinese trading-platform environment, and a backtest simulates how a strategy would have traded using historical data.
A research workflow based on Chan theory, a method of analysing market price structures across several time levels. It turns concepts such as trends, pivots, divergence, and buy or sell points into reproducible study or backtesting rules.
The single entry point that executes a Public Portfolio Challenge episode or addendum runbook end-to-end, delegating each stage to the functional skills. Use when asked to run/execute/replay Episode 10, its bakeoff, or its addendum with the NexusTrade MCP connected. Reads the target runbook, pins its real artifacts…
Run a multi-family strategy bakeoff — the SEARCH→CERTIFY funnel that screens many candidate mechanisms down to a certified deploy winner without letting the cheap search layer issue a verdict. Use when replaying the Episode 10 bakeoff, when exploring several distinct strategy families before certifying, when deciding…
Run and read a NexusTrade walk-forward out-of-sample study — the certification engine behind the Public Portfolio Challenge. Use when certifying a fixed portfolio (backtestonly) or re-optimizing one (sweep), when setting foldcount / anchored / validation / embargo params, when monitoring a runwalkforwardstudy to…
Backtesting and simulation: vectorized backtesting, paper trading simulation, strategy A/B testing, automated strategy building, natural language to strategy, and trading plan generation. USE FOR: backtest, backtesting, paper trading, simulation, strategy builder, A/B test strategies, natural language strategy…
An A-share stock analysis and selection tool for China’s stock market. It combines market data, company measures, price-pattern analysis, scores, signals, and a managed list of stocks.
This skill creates disciplined investment retrospectives for public-market equities by starting from abnormal price windows and testing candidate drivers before generating a narrative.
A research workflow for tracking the life cycle of an investment theme and identifying the companies or other assets best connected to it. It separates broad industry research, theme-based research, and analysis of individual stocks.
Quant single-stock research orchestrator for A-share, H-share, U.S. equity, A/H, and ADR/HK L2+/L3 work. Use for single-stock research, held-position refresh, stock comparison, action semantics, and closeout-ready five-file packages. Broad stock discovery must route to l3-candidate-queue before full L3.