stock-research SKILL.md skillA

stock-research from qusong0627/quantmind is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add qusong0627/quantmind/stock-research@git:20261003.8b2ea6a

Pins git:20261003.8b2ea6a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
qusong0627/quantmind
Path
skills/stock-research/SKILL.md
Versions recorded
5
Latest version
git:20261003.8b2ea6a, committed Oct 3, 2026
First version recorded
Aug 29, 2026
Size
7,226 bytes
Repository stars
1,774
License
AGPL-3.0

个股深度研究(多 Agent 编排版)— 多角色分析师并行编排(技术/新闻/资金情绪/基本面/市场 5 分析师并行 → 多空辩论 → 研究经理汇总),数据全部走 QuantMind 本地(QuantDB + PG 新闻富集 + Huntly),新闻双通道(自家 FinBERT 量化情绪 + 实时搜索补充)。用户说「深度研究」「个股深度研究」「研究某只股票」「多角度分析」时使用:跑 research_data.py 取数 → 并行分析师 → 辩论 → 汇总报告 → PDF → 落盘深度分析目录。触发词:深度研究、个股研究、研究600519、多角度分析、全面分析某股.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

> ⚙️ 本技能遵循公共运行环境契约(最高优先级,先于本文其余内容执行):
> 详见 [_shared/env-contract.md](../_shared/env-contract.md),执行前先读它。

# stock-research — 个股深度研究(多 Agent 框架版)

把多角色投研编排落地到 QuantMind:**数据 100% 走本地**(QuantDB parquet + PG 新闻富集 + Huntly),**新闻双通道**(自家 FinBERT 情绪量化 + WebSearch 实时补充),输出研报级 MD + PDF,落盘深度分析目录(报告管理页 → A股市场 → {股票名})。

与 [[stock-deep-research]](智能体自主版深度投研)**不冲突,互为补充**:
- 本 skill = 5 分析师并行编排的「多 Agent 框架版」,流程更重、结构化更强;
- [[stock-deep-research]] = 轻量自主版(特征快照 → 多空子代理辩论 → 综合研判),任何大模型可跑;
- 两者**数据同源**(QuantDB + PG),本 skill 额外整合了**模型推理分数**(engine_signal_scores)与**新闻类型分布**;
- 结论冲突时以数据为准:每个数字都可在数据包溯源,也可读归档目录下已有报告(`A股市场/{股票名}/`)交叉验证。

## 架构

```
Phase 1(并行 5 分析师,各读同一份数据包的不同切片):
  技术面 → 趋势/均线/指标/量价
  新闻面 → 自家 FinBERT 情绪(主)+ WebSearch 实时新闻(辅)
  资金情绪 → L2 主力资金流 + 换手/量能
  基本面 → 估值 + 财务三表核心科目
  市场面 → 大盘背景 + 所属行业强弱 + 板块资金流
Phase 2(并行):多头研究员 vs 空头研究员(基于 facts 辩论,禁编数据)
Phase 3:研究经理汇总 → 结论(评级/目标区间/风险/跟踪信号)
输出 → md → PDF → 落盘
```

## ⚠️ 数据铁律(最高优先级,所有 Agent 必须遵守)

1. **禁止伪造数据**:所有价格/PE/财务/资金流数字必须来自数据包 JSON,严禁编造
2. **数据包是唯一数据源**:先跑 `research_data.py` 拿到 `{symbol}_{date}.json`,各分析师只读该文件对应切片;WebSearch 只允许补充**新闻面**的时效性(不得用于取行情/财务)
3. **过期标注**:数据包 generated_at 距今 >5 个交易日时,报告开头标注 `⚠️ 数据截止 {generated_at}`;财报报告期为上季度时注明
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add qusong0627/quantmind/stock-research@sha256:f6565506d867b714

The line at the top of this page pins the label git:20261003.8b2ea6a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5jqua3hgkfce7pjj.svg)](https://markdownregistry.com/a/art_5jqua3hgkfce7pjj)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 29, 2026 and Oct 3, 2026, about one every 9 days. Its first recorded version is graded B and its latest A.

versioncommittedcommitsizeaudit
git:20261003.8b2ea6a latest2026-10-03 8b2ea6a 7,226 BA view · diff
git:20260919.a5c80062026-09-19 a5c8006 7,307 BA view · diff
git:20260830.821e7732026-08-30 821e773 9,390 BB view · diff
git:20260829.c9fd96c2026-08-29 c9fd96c 9,104 BB view · diff
git:20260829.cda0e482026-08-29 cda0e48 9,112 BB view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7226 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

qusong0627/quantmind · 1,774 stars · license AGPL-3.0 · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_5jqua3hgkfce7pjj
GET https://markdownregistry.com/api/v1/resolve?ref=qusong0627/quantmind/stock-research
GET https://markdownregistry.com/api/v1/blob/f6565506d867b714f7cd786f6f99e62b385c7dab2f9acdea1ca2ce13d7a7d05a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from qusong0627/quantmind

AGENTS.md AGENTS.md file
qusong0627/quantmind · AGENTS.md
git:20261021.501dee8 · audit B · 1,774 stars
CLAUDE.md CLAUDE.md file
qusong0627/quantmind · CLAUDE.md
git:20261003.8b2ea6a · audit A · 1,774 stars
AGENTS.md@config/qwenpaw AGENTS.md file
qusong0627/quantmind · config/qwenpaw/AGENTS.md
git:20261003.8b2ea6a · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/claude AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/claude/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/codex AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/gemini AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/gemini/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
ai-ide-strategy-writing SKILL.md skill
qusong0627/quantmind · skills/ai-ide-strategy-writing/SKILL.md · AI-IDE 写策略与执行 — 用 AI 生成 Qlib 量化策略代码、Docker 容器执行策略/回测、自然语言条件选股、策略落库。在 QuantBot / Claude Code 中让 AI 写策略、生成 Qlib…
git:20260919.a5c8006 · audit B · 1,774 stars
backtest-center SKILL.md skill
qusong0627/quantmind · skills/backtest-center/SKILL.md · 回测中心 — 快速回测、专家模式、回测历史、策略对比、参数优化、策略管理、高级分析。在 QuantBot / Claude Code 中运行 Qlib…
git:20260919.a5c8006 · audit B · 1,774 stars
batch-inference-analysis SKILL.md skill
qusong0627/quantmind · skills/batch-inference-analysis/SKILL.md · 批量推理结果分析 — 用 QuantMind 选股策略方法论分析每日信号、行业轮动、个股分数区间、负分参考。在 QuantBot / Claude Code…
git:20260919.a5c8006 · audit B · 1,774 stars
daily-review SKILL.md skill
qusong0627/quantmind · skills/daily-review/SKILL.md · A股每日复盘(专业版)— 基于 QuantDB 本地数据 + 当日新闻情绪 + 模型推理信号 + L1/L2 因子截面 + 板块资金流的盘后复盘:指数、涨跌结构与涨停梯队、量能、行业/概念轮动、资金面、L2…
git:20261003.8b2ea6a · audit A · 1,774 stars
futuapi SKILL.md skill
qusong0627/quantmind · skills/futuapi/SKILL.md · 富途 OpenAPI 交易与行情助手。查询行情、K线、报价、快照、买卖盘、逐笔成交、分时数据;搜索标的与资讯;解析期权代码、查询期权链/到期日/IV/行权概率;执行买入/卖出/下单/撤单/改单;查询持仓/资金/账户/订单;订阅实时推送;加密…
v0.1.1 · audit A · 1,774 stars
install-futu-opend SKILL.md skill
qusong0627/quantmind · skills/install-futu-opend/SKILL.md · Futu OpenD 安装助手。自动下载安装Futu OpenD 并升级 Python SDK。支持 Windows、MacOS、Linux。用户提到安装、下载、启动、运行、配置 OpenD、开发环境、升级 SDK、futu-api…
v0.1.1 · audit A · 1,774 stars

Every file in qusong0627/quantmind

Browse by kind, by grade A, or by owner.