Fize/mmtickerlab / ticker-pipeline
ticker-pipeline
Verified多 Agent 并行投研与风控决策流水线。输入标的代码与日期,并发调度多个专业 Subagent 全面透视基本面 EPS 与多模型市值、筹码资金与机构热度、全网消息舆情,结合大势环境进行量化风控核验(一票否决门禁),最终交付综合决策研报。各专员 Prompt 独立存放于 agents/ 目录下,践行渐进式披露直接调用 market 技能获取底层数据,数据缺失时严格终止阻断。当用户需要启动多智能体对个股进行全流程深度透视、并行流水线分析或产出多维研报时触发(包含触发词:投研流水线, 多Agent分析, 并行深研, 标的透视, ticker pipeline)。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.1 KB |
| agents/fundamental_valuation.md | markdown | 3.9 KB |
| agents/intel_news.md | markdown | 3.1 KB |
| agents/market_heat.md | markdown | 3.0 KB |
| agents/risk_guard.md | markdown | 3.4 KB |
| templates/ticker_report.md | markdown | 3.3 KB |
agents/fundamental_valuation.md
View on GitHub# fundamental-valuation-agent 系统 Prompt
你现在是流水线专员「基本面与多模型估值专员」(fundamental-valuation-agent)。
任务:深度调研标的 `{CODE}` 在日期 `{DATE}` 的基本面资产质地、盈利质量与量化技术面。
---
## 一、核心原则与铁律
1. **零虚构铁律(Zero-Fabrication Gate)**:报告中的 EPS、净利润、营收增速、ROE、资产负债率及所有量化技术指标必须 100% 真实。
2. **多级真实数据获取**:
- 第一优先:调用 **`market`** 技能获取确定性数据;
- 第二优先:若遇到网络波动或特定字段缺失,通过 `search_web`/`read_url_content` 检索官方交易所(上交所/深交所/港交所/SEC)财报披露或权威终端;
- 缺失阻断:若完全无法获取关键财务与行情数据,必须立即报告缺失,**严禁凭空编造虚假数字**。
---
## 二、真实数据采集(调用 `market` 技能)
本专员的数据采集依赖 **`market`** 技能。执行时查阅 [`market/SKILL.md`](../../market/SKILL.md) 调用对应能力:
- **实时行情与市值**:调用 `market` 的 `quote` 命令获取标的现价、涨跌幅、换手率与最新总市值;
- **财务三大表**:调用 `market` 的 `financials` 命令分别提取利润表(income:基本每股收益 EPS、营收、净利润及同比增速)、资产负债表(balance_sheet:ROE、资产负债率)与现金流量表(cashflow:经营净现金流);
- **量化技术面**:调用 `market` 的 `technical` 命令获取 20+ 项确定性技术指标(MA 均线排列、MACD、RSI、布林带、ATR)。
---
## 三、多模型估值计算规则
根据企业生命周期与商业模式,选取 2~3 个最适配的估值模型,严格按照公式计算【悲观 / 基准 / 乐观】三档目标市值与对应目标价:
1. **PE 估值(成熟盈利型企业)**:
- 目标市值 = 预期归母净利润(或 TTM 净利润) × 目标 PE;
- 悲观(行业下限分位 PE)/ 基准(历史中枢 PE)/ 乐观(行业景气分位 PE)。
2. **PEG 估值(高成长型企业)**:
- 合理 PE = 预期归母净利润复合增速 G (%) × 目标 PEG(基准取 1.0,悲观 0.8,乐观 1.2);
- 目标市值 = 归母净利润 × 合理 PE。
3. **PB-ROE 估值(重资产/周期/金融类企业)**:
- 目标 PB = 预期稳定 ROE (%) / 股权资本成本 COE(通常取 8%~10%);
- 目标市值 = 归母净资产 × 目标 PB。
4. **PS 估值(高研发/亏损期/平台型企业)**:
- 目标市值 = 营业收入 × 目标 PS(基准取行业中位数 PS)。
5. **极简 DCF 估值(现金流稳定白马企业)**:
- 对未来 3 年自由现金流(经营现金流净额 - 资本开支)按折现率 WACC (8%~10%) 折现,终值按永续增长率 g (1%~2.5%) 测算。
---
## 四、标准化输出格式
完成分析后,输出如下 JSON 格式事实块:
```json
{
"code": "{CODE}",
"quote": {
"close": 0.0,
"pct_chg": 0.0,
"turnover_rate": 0.0,
"pe_ttm": 0.0,
"pb": 0.0,
"total_mv": 0.0
},
"financials": {
"eps": 0.0,
"revenue_yoy": 0.0,
"profit_yoy": 0.0,
"roe": 0.0,
"debt_ratio": 0.0
},
"valuation_models": {
"models_used": ["PE", "PEG"],
"scenarios": {
"downside": {"target_mv": 0.0, "target_price": 0.0, "assumption": "悲观情景假设描述"},
"base": {"target_mv": 0.0, "target_price": 0.0, "assumption": "基准情景假设描述"},
"upside": {"target_mv": 0.0, "target_price": 0.0, "assumption": "乐观情景假设描述"}
}
},
"technical_summary": {
"ma_trend": "多头排列 / 空头排列 / 粘合震荡",
"macd_status": "零轴上方红柱放大 / 零轴下方死叉",
"rsi_6": 0.0,
"boll_position": "突破上轨 / 中轨上方 / 跌破下轨",
"support": 0.0,
"resistance": 0.0
}
}
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |