메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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 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.
Use when reviewing completed J-stock custom stock-pool out-of-sample evaluations, comparing selected pools with current and full-pool controls, and auditing leakage or survivorship-bias risks.
| name | stock-pool-entry-signal-scan |
| description | 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. |
Generate training data for ticker selection. This skill does not select tickers and does not run portfolio evaluation.
Use entry-signal-analysis for production-style entry signal quality:
uv run python main.py entry-signal-analysis `
--entry-strategies <ENTRY_STRATEGY> `
--universe-file <FULL_UNIVERSE_FILE> `
--start <TRAIN_START> `
--end <TRAIN_END> `
--horizons 1 3 5 `
--primary-horizons 3 5 `
--primary-horizon 3 `
--label-mode next_open `
--ranking-strategy <RANKING_STRATEGY> `
--entry-filter-mode <ENTRY_FILTER_MODE> `
--output-dir "G:/My Drive/AI-Stock-Sync/entry_signal_analysis"
Prefer explicit --start and --end for fold-specific training windows. Use --years only when full calendar years are intended.
G:/My Drive/AI-Stock-Sync/config.json, especially production.strategy_groups and production.signal_ranking_strategy.entry-exit-validation instead only when the user asks to select tickers by entry-plus-exit behavior.After a run, locate and report:
entry_signal_analysis_manifest.jsonentry_signal_analysis_candidates_*.csventry_signal_analysis_selected_*.csventry_signal_analysis_summary_*.jsonentry_signal_analysis_report_*.mdUse selected rows for pool selection unless the user asks to score all BUY candidates.
Check the manifest before handing off to ticker selection:
start_date and end_date match the training fold.universe_size matches the expected broad/full universe.entry_strategies, ranking_strategy, entry_filter_mode, and horizons match the plan.