菜单
Execute the Hermes A-share theme-structure SOP closing snapshot pipeline. Use when the user asks to run the closing snapshot, generate post-market sentiment/theme/performance outputs, or update hermes/outputs/ with today's closing data.
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 Gordon asks to analyze A-share theme structure, sector rotation, leader pullbacks,补涨,连板/炸板情绪, or to build a research-only watchlist using a reusable four-tier SOP engine (L1宏观→L2题材→L3个股→L4执行).
L1 macro market filter for the A-share theme structure SOP engine. Use to determine whether the overall market environment supports trading — outputs 系统性风险/震荡市/多头趋势 and gates downstream modules.
L2 dynamic theme structure & sentiment engine for the A-share SOP. Use to identify main themes, classify theme lifecycle stage, assess quantitative health indicators, and produce layered stock pools with 5-factor scoring.
L3 stock resonance & risk control engine for the A-share SOP. Use to score individual stocks against buy/sell rules, apply theme state gates, and output 候选观察 or 风控观察 alerts with cooling mechanism.
L4 execution & review engine for the A-share SOP. Use to convert L3 candidate signals into trade plans (with stop/target/R:R), perform manual confirmation, journal trades, and run weekly review & attribution.
| name | hermes-closing-snapshot |
| description | Execute the Hermes A-share theme-structure SOP closing snapshot pipeline. Use when the user asks to run the closing snapshot, generate post-market sentiment/theme/performance outputs, or update hermes/outputs/ with today's closing data. |
| agent_created | true |
sentiment_YYYY-MM-DD.json、theme_hypothesis_YYYY-MM-DD.json、performance_YYYY-MM-DD.jsonwestock-mcp / westock-data，输出目录为 hermes/outputs/westock-mcp:
mcp__westock-mcp__data_quote for sh000001,sz399001,sz399006mcp__westock-mcp__data_kline for the same indices (day, limit 20)mcp__westock-mcp__data_changedist with {"type":"0"} for up/down/limit countsmcp__westock-mcp__data_market_overview with type=trade,updown,summarymcp__westock-mcp__data_sector with mode=ranking,limit=50 for sector gainers & fund flowhermes/data/market_snapshot.json with closing fields:
date, session: "close", index_changes, index_closes, index_kline_closeup_count, down_count, flat_count, up_down_ratiolimit_up_count, limit_down_count, volume_ratio, total_amount_yi, amount_change_yinorthbound_flow (set to 0 if no live field available)consecutive_days.limit_up_trend = "rising"/"falling" vs previous sessionhot_boards, sector_data, limit_pool_close, stocks: []hermes/data/candidate_history.json exists (create [] if missing).--date YYYY-MM-DD:
hermes/scripts/sentiment_snapshot.pyhermes/scripts/theme_hypothesis.pyhermes/scripts/performance_tracker.pyhermes/outputs/ and present them to the user.WorkBuddy/.workbuddy/memory/YYYY-MM-DD.md).research_only boundary: do not emit actionable buy/sell advice; only analysis, regimes, and scoring.DISCORD_WEBHOOK_URL is unset; this is expected.candidate_history.json is empty, performance_tracker.py will report 0 candidates.