Menü
SkillsMP hat 355 Skills aus XinAloha/skills gesammelt. Öffne einen Skill, um Quelle und Details zu prüfen.
Es werden 40 von 355 gesammelten Skills angezeigt.
Use when an agent needs a standard cross-sectional long-only backtest protocol with T+1 open execution, top-bucket equal weighting, fees, limit-up or limit-down exclusions, benchmark comparison, NAV curves, drawdown, IC, and diagnostic charts.
Quellsprache: Chinesisch
Brinson-Fachler / BHB sector attribution with interaction, concentration (HHI), top contributors, and optional Carino multi-period linking. Use to explain active return as allocation vs selection.
Quellsprache: Chinesisch
Run and explain cross-sectional trading-factor backtests on schema-compatible factor signals and market data. Use when Codex needs to validate backtest inputs; calculate returns, NAV, drawdown, holdings, turnover, benchmark or hedged performance; generate a…
Quellsprache: Englisch
Decompose a portfolio's active return versus its benchmark into sector allocation, stock selection, and interaction (Brinson-Fachler + Carino multi-period linking) plus factor contributions (cross-sectional regression), answering where the excess return came…
Quellsprache: Chinesisch
Turn an alpha signal into optimal portfolio weights under real constraints. Use when a user has factor scores / expected returns and wants portfolio weights, or asks about mean-variance / risk-parity / minimum-variance / maximum-diversification optimisation,…
Quellsprache: Chinesisch
Risk/return dossier for ONE symbol over a window: annualized return, volatility, Sharpe, Sortino, max drawdown, Calmar, win-rate. Auto-routes A-share / HK / US by suffix. Use when the user asks "how risky / how good is X", or wants 夏普 / 最大回撤 / 年化 over a…
Quellsprache: Englisch
A-share / cross-market transaction cost analysis (TCA). Use when a user has trade fills or backtest turnover and asks "how much did execution actually cost". Decomposes implementation shortfall into timing, market impact (square-root model), spread,…
Quellsprache: Chinesisch
Calibrate commissions, bid-ask spread, slippage, and simple market-impact assumptions from executions, quotes, or OHLCV data. Use when an agent needs an auditable transaction-cost model for backtest assumptions, execution review, or capacity analysis.
Quellsprache: Englisch
Use when building or auditing A-share financial-factor backtests that must avoid look-ahead bias from current or restated financial reports. Produces historical as-of financial datasets for rebalance dates and verifies whether factor/backtest inputs used only…
Quellsprache: Chinesisch
Use when raw close, adjusted close, cash-dividend, and split-factor data must be checked for invalid event inputs, unexplained price jumps, or adjusted-return mismatches before equity research or backtesting.
Quellsprache: Chinesisch
Use when normalized intraday OHLCV bars must be checked for duplicate or non-monotonic timestamps, missing intervals, invalid price relationships, non-positive prices, negative volume, or trading-date mismatches before research or backtesting.
Quellsprache: Chinesisch
Use this skill to evaluate Alpha factors with IC/RankIC, ICIR, stratified backtests, turnover, decay curves, stock-pool filters, statistical diagnostics, and standalone HTML reports.
Quellsprache: Englisch
当需要对 Alpha 因子进行 IC 测试与因子评估时，使用此 skill。该 BUILD 提供 IC/RankIC、ICIR、时间稳定性、分布诊断、分层回测、换手率、衰减曲线、股票池筛选和科研级 HTML 可视化报告生成能力，可被 agent 或 Alpha 调用。
Quellsprache: Chinesisch
当需要读取 IC测试与因子评估体系 的生产结果时，使用此 skill。该 skill 读取已生成的 Parquet 结果，不重复执行重计算流程。
Quellsprache: Chinesisch
Compute Alpha101 and Alpha191 factor-library values based on JoinQuant formulas from long-form OHLCV CSV market data. Use when an agent needs to calculate selected or full Alpha101/Alpha191 factor columns, export wide factor CSVs, and list skipped factors…
Quellsprache: Englisch
Use when an agent needs to blend multiple evaluated quantitative factor signals into a single composite alpha signal (signal-level merge, not portfolio-level combination). Covers factor selection, redundancy removal, weighting, and composite evaluation.
Quellsprache: Chinesisch
Use when an agent needs to evaluate a single quantitative factor or signal with rank IC, Pearson IC, Sharpe, maximum drawdown, monotonicity, turnover, and a normalized composite score report.
Quellsprache: Chinesisch
Generate initial stock alpha ideas with economic rationale and concrete factor shapes, defaulting to daily OHLCV when no fields are specified. Use when a user says they have run out of factor ideas or asks for new factor directions, structured hypotheses,…
Quellsprache: Chinesisch
当需要开发、审查、验证或排错单因子股票 alpha 时，使用此 skill。适用于 A 股/港股/美股等权益市场的横截面选股、单因子回测、IC/IR 分析、行业/市值/beta 中性化、股票池过滤、未来函数检测、换手成本诊断和因子失效归因。
Quellsprache: Chinesisch
Use when an agent needs a disciplined quantitative factor mining workflow for forming one hypothesis at a time, implementing a factor, running validation, recording iteration notes, accepting improvements, or rolling back weak experiments.
Quellsprache: Chinesisch
当 agent 需要对一个已有股票或期货因子做原地优化时使用：复用项目本地数据和评价引擎，扫描关键 period 参数，在 best period 上做组件消融，从 core 版本出发做 refinement，并在文件报告和对话回答中同时给出指标表、稳健性讨论和是否替换原因子的结论。Use for optimizing one existing stock or futures factor with period sweeps, ablations, refinements, robustness…
Quellsprache: Chinesisch
Use when an agent needs to neutralize or orthogonalize a quantitative factor against industry, size, style exposures, or an existing factor library before evaluating, combining, or accepting the signal.
Quellsprache: Chinesisch
Run one round of factor-pool recommendation from an existing stock alpha set. Use when an agent needs to start from user-provided seed factors, prepare mutation and crossover prompt packs for the current model to reason over, then evaluate generated factors…
Quellsprache: Chinesisch
Rank and select quantitative model factors from local factor and label CSV files with regression mRMR using F-statistic relevance and Pearson redundancy, or fixed-model Marginal-SAGE MSE contribution for LGBM and MLP. Use when an agent needs reproducible…
Quellsprache: Englisch
Use when an agent needs to review an existing factor library, summarize experiment logs, quantify acceptance rates and score dynamics, analyze factor families and correlations, and recommend the next research direction.
Quellsprache: Chinesisch
Run a self-contained FactorMAD-style LLM multi-agent debate workflow for mining interpretable code-based stock alpha factors from daily OHLCV and point-in-time fundamental data. Use when an agent needs to generate, debate, validate, score, and export OHLCV,…
Quellsprache: Englisch
Compute, validate, and analyze fundamental (financial statement) factors for Chinese A-shares. Covers value (EP, BP, SP, CP, FCFP, GP/A), quality (ROE, ROA, gross margin, accruals, leverage), growth (earnings growth, revenue growth, analyst revision), and…
Quellsprache: Englisch
Use when an agent needs multidimensional IC diagnostics for a quantitative signal, including rank versus Pearson IC, IC decay, subsample IC, top-basket Jaccard stability, and cumulative IC timelines.
Quellsprache: Chinesisch
Combine many existing alpha factors into one out-of-sample meta-signal with a leakage-safe rolling walk-forward and Purged & Embargoed K-fold CV (Lopez de Prado). Trains LightGBM / ElasticNet / Ridge per window, stitches OOS predictions, reports feature…
Quellsprache: Englisch
Discover and validate cross-sectional alpha factors for Hong Kong and US equities - generate candidate factors, compute them, and screen by IC, decay, and turnover. Use when a user wants to mine, test, or rank overseas equity factors from Pandadata HK/US…
Quellsprache: Englisch
Use when an agent needs a verified library of directional OHLCV alpha factor Skills for trend, breakout, reversal, channel-position, or price-direction research across A-share and US equity samples.
Quellsprache: Englisch
Use when an agent needs a verified library of OHLCV risk-state and chart-pattern alpha factor Skills for volatility, K-line shape, shock, drawdown, and pressure analysis.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Volume Expansion factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Volume Z-Score factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Dollar Volume Activity factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Price Volume Correlation factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored OBV Slope factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Close TS Rank factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Volume TS Rank factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch
Use when computing the 5D Z-Scored Return Skewness factor from user-supplied real OHLCV data or reviewing its bundled real-data validation metrics.
Quellsprache: Englisch