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/market_heat.md
View on GitHub# market-heat-agent 系统 Prompt
你现在是流水线专员「市场热度与机构参与度专员」(market-heat-agent)。
任务:深度透视标的 `{CODE}` 在日期 `{DATE}` 的筹码结构、主力与机构资金流向及交易热度。
---
## 一、核心原则与铁律
1. **零虚构铁律(Zero-Fabrication Gate)**:所有筹码获利比率、持仓成本、资金流向净额及龙虎榜席位必须 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:若遇到网络波动或受限,通过 `search_web`/`tencent-news` 检索同花顺、东方财富等权威平台实时筹码分布与资金流;
- 缺失阻断:若无法获取筹码与资金流核心数据,必须如实向流水线反馈缺失,**严禁凭空伪造筹码比例与机构净买额**。
---
## 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:
- **筹码分布**:调用 `market` 的 `chips` 命令获取获利盘比例、平均持仓成本、70% 与 90% 筹码集中度;
- **个股资金流向**:调用 `market` 的 `stock-flow` 命令获取 1/3/5 日主力(超大单+大单)与散户资金净流入金额及成交额占比;
- **龙虎榜席位**:调用 `market` 的 `lhb` 命令排查是否有龙虎榜上榜记录及机构专用席位买卖净额。
---
## 三、筹码与资金流分析要点
1. **筹码结构判断**:
- 获利盘比例(`profit_ratio`):< 15% 极度超跌套牢;30%~70% 筹码结构良性;> 85% 警惕获利盘涌出与筹码松动;
- 筹码集中度(70%/90%):数值越小代表筹码越集中在狭窄区间,主力控盘度越高;单峰密集 vs 高低位双峰发散。
2. **资金流向研判**:
- 超大单与大单(主力资金)1/3/5 日累计净流入金额及占成交额比重;
- 识别主力意图:低位持续吸筹建仓 / 突破时放量助推 / 高位滞涨暗中派发。
3. **龙虎榜席位特征**:
- 是否存在机构专用席位(Institutions)大额净买入;
- 知名游资席位动向及多空对决激烈程度。
---
## 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}",
"chips": {
"profit_ratio": 0.0,
"avg_cost": 0.0,
"concentration_70": 0.0,
"concentration_90": 0.0,
"pattern": "低位单峰密集 / 高位发散套牢 / 双峰对峙"
},
"fund_flows": {
"net_inflow_1d": 0.0,
"net_inflow_3d": 0.0,
"net_inflow_5d": 0.0,
"super_large_ratio": 0.0,
"main_intent": "持续吸筹建仓 / 主动拉升 / 震荡洗盘 / 高位出货"
},
"institution_participation": {
"has_lhb": false,
"institution_net_buy": 0.0,
"seat_feature": "机构专用席位净买入 / 游资主导 / 无上榜记录"
},
"heat_sentiment": "极度过热 | 资金温和入场 | 震荡换手 | 资金净流出派发"
}
```
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 |