llm-quant/app/data/prompt_templates/department_base@1.0.0.json

30 lines
1.6 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"department_base": {
"name": "部门基础模板",
"description": "所有部门通用的审慎分析提示词骨架",
"template": "\n部门{title}\n股票代码{ts_code}\n交易日{trade_date}\n\n【角色定位】\n- 角色说明:{description}\n- 行动守则:{instruction}\n\n【数据边界】\n- 可用字段:\n{data_scope}\n- 核心特征:\n{features}\n- 市场背景:\n{market_snapshot}\n- 追加数据:\n{supplements}\n\n【分析步骤】\n1. 判断信息是否充分,如不充分,请说明缺口并优先调用工具 `fetch_data`(仅限 `daily`、`daily_basic`)。\n2. 梳理 2-3 个关键支撑信号与潜在风险,确保基于提供的数据。\n3. 结合量化证据与限制条件,给出操作建议和信心来源,避免主观臆测。\n\n【输出要求】\n仅返回一个 JSON 对象,不要添加额外文本:\n{{\n \"action\": \"BUY|BUY_S|BUY_M|BUY_L|SELL|HOLD\",\n \"confidence\": 0-1 之间的小数,\n \"summary\": \"一句话结论\",\n \"signals\": [\"关键支撑要点\", \"...\"],\n \"risks\": [\"关键风险要点\", \"...\"]\n}}\n如需说明未完成的数据请求请在 `risks` 或 `signals` 中明确。\n",
"variables": [
"title",
"ts_code",
"trade_date",
"description",
"instruction",
"data_scope",
"features",
"market_snapshot",
"supplements"
],
"required_context": [
"ts_code",
"trade_date",
"features",
"market_snapshot"
],
"metadata": {
"category": "department",
"preset": "base"
},
"version": "1.0.0",
"activate": false
}
}