菜单
Use when aggregating J-stock training-period entry-signal-analysis or entry-exit-validation CSV artifacts by ticker, scoring ticker robustness, and exporting selected stock-pool universe JSON files for out-of-sample evaluation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when: generating worker-ready JSON manifests for J-stock evaluation, pos-evaluation, walk-forward-evaluate, or replay-evaluation batch execution. Resolve WebUI-equivalent defaults, split jobs by worker during generation, and stop before execution.
Use when: orchestrating an end-to-end J-stock batch evaluation workflow, or when the user explicitly names evaluation-batch-runner. Schedule evaluation-batch-generator, evaluation-batch-executor, and evaluation-result-summary in order, preserving the manifest approval boundary and allowing subagent delegation only during approved execution.
Use when: aggregating completed J-stock evaluation output directories into markdown summary reports under G:/My Drive/AI-Stock-Sync/summary without rerunning backtests, including global MDD-Win re-scoring via tools/score_evaluation_outputs.py when worker-local PRS is not comparable.
Use when generating training-window entry-signal-analysis datasets for a J-stock stock-pool experiment, especially scanning a broad/full universe with a fixed entry strategy before ticker-level pool selection.
Use when orchestrating a J-stock custom stock-pool experiment where a fixed entry condition is applied to a broad/full universe during a training window, good tickers are selected into one or more test universes, and those universes are evaluated out-of-sample against current and full-pool controls.
Use when generating approval-ready J-stock out-of-sample evaluation commands or batch manifests that compare trained selected stock pools against current production and broad/full universe controls.
| name | stock-pool-ticker-selector |
| description | Use when aggregating J-stock training-period entry-signal-analysis or entry-exit-validation CSV artifacts by ticker, scoring ticker robustness, and exporting selected stock-pool universe JSON files for out-of-sample evaluation. |
Convert training-period signal results into fixed ticker universe files.
Use one of these training-only artifacts:
entry_signal_analysis_selected_*.csv.entry_signal_analysis_candidates_*.csv.combo_selected_trades.csv from entry-exit-validation.Require a known training cutoff. Reject or flag rows with signal_date or entry_date after the training end date.
Aggregate by normalized ticker code. Compute at least:
sample_countactive_year_countwin_rateavg_returnmedian_returntrimmed_mean_5pctp10_returnp25_returntop_5pct_contribution_ratiomean_without_top_5pct_returnFor entry-signal-analysis, use the planned primary return column such as forward_return_3d_pct or forward_return_5d_pct. For entry-exit-validation, use return_pct.
Default gates:
sample_count >= 20 for short training windows, or >= 30 for multi-year training windows.top_5pct_contribution_ratio > 0.5 or mean_without_top_5pct_return is negative.Default score order:
trimmed_mean_5pct.median_return.p10_return.win_rate.top_5pct_contribution_ratio.sample_count.Export JSON that src.utils.universe_loader.load_tickers_from_file can read:
{
"version": "1.0",
"pool_id": "selected_top140_train_2022_2025",
"created_at": "YYYY-MM-DDTHH:MM:SS",
"selection_source": "<training CSV path>",
"train_start": "YYYY-MM-DD",
"train_end": "YYYY-MM-DD",
"target_size": 140,
"tickers": [
{
"code": "7203",
"rank": 1,
"score": 1.234,
"sample_count": 42,
"active_year_count": 3
}
]
}
Write selected-pool artifacts under G:/My Drive/AI-Stock-Sync/universe/ unless the user requests a repo-local fixture.
load_tickers_from_file.