quantskills/agent-quantspace

analyze

Use when tasks need factor diagnostics, IC/grouped return analysis, attribution, robustness checks, deterministic factor-mining evaluation, or time-series distribution and stationarity checks.

compute

Use when tasks need strategy-agnostic OHLCV indicators, math utilities, generic factor examples, regime slicing, resampling, or label makers.

factor-mining

Use when tasks need AI multi-agent factor mining research boundaries, versioned ResearchBrief/FactorSpec contracts, evaluation/review/decision objects, or cross-platform role task protocols without implementing compute/analyze algorithms here.

ml

Use when tasks need optional PyCaret model training, ML factor generation, inference wrappers, feature importance, or sparse LASSO weight generation.

report

Use when tasks need complete HTML research reports, HTML dashboards, PNG chart helpers, or files under the research reports directory.

strategy

Use when tasks need reusable strategy contracts, cross-sectional selection types, or time-series signal-to-weight helpers.

backtest

Use when tasks need vectorized strategy execution, portfolio weighting, portfolio-level filters, transaction cost helpers, exit A/B analysis, overlay metrics, or multi-strategy return blending.

ingest

Use when tasks need PandaData/PandaAI stock, fund, ETF, index, or futures data, reference data, adjustment factors, futures tick downloads, or symbol conversion.

store

Use when tasks need local market Parquet data, factor artifacts, backtest data, or model files through DataManager.

research

Use when tasks need reusable research pipeline templates, factor screening, or parameter sensitivity sweeps.