Skip to content
Back to search

Claude-Code-Stock-Deep-Research-Agent

本研究基于 Claude Code Deep Research 系统: 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用:/stock-research AAPL, I want a quick overview

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/liangdabiao--claude-code-stock-deep-research-agent/badge.svg)](/listings/liangdabiao--claude-code-stock-deep-research-agent)

HTML

<a href="/listings/liangdabiao--claude-code-stock-deep-research-agent"><img src="/api/listings/liangdabiao--claude-code-stock-deep-research-agent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Stock Research (股票投资尽调)

# Start Claude Code
claude

# Set model (optional, but recommended)
/model opus

# Execute stock research
/stock-research [股票代码或公司名称]

# Examples:
/stock-research 600519              # 贵州茅台 (A-share)
/stock-research AAPL                # 苹果公司 (US)
/stock-research 腾讯 00700.HK       # 腾讯控股 (HK)

**The system will**: 1. Ask about your investment style (价值/成长/困境/红利), holding period, risk tolerance 2. Deploy ~28 parallel research agents across 7 phases 3. Generate comprehensive due diligence report in `RESEARCH/STOCK_[ticker]_[company]/`

**Time**: 2-4 hours for standard due diligence

Output Example

RESEARCH/STOCK_600519_Kweichow_Moutai/
├── 00_Executive_Summary.md        # 🟡🟡🟡 Hold / Fairly Valued
├── 01_Business_Foundation.md      # Products, revenue, customers
├── 02_Industry_Analysis.md        # Industry cycle, competition
├── 03_Business_Breakdown.md       # Profit drivers, economics
├── 04_Financial_Quality.md        # Cash flow, margins, red flags
├── 05_Governance_Analysis.md      # Ownership, management
├── 06_Market_Sentiment.md         # Bull/bear cases
├── 07_Valuation_Moat.md           # Moat rating, valuation
├── Financial_Data/                # Metrics, trends, peer comparison
├── Valuation/                     # DCF, scenarios
├── Risk_Monitoring/               # Bear case, monitoring checklist
└── sources/                       # Citations with quality ratings

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 384 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Code Stock Deep Research Agent
  2. **Investment Research Edition** - 专业股票投资尽调系统
  3. ⚖️ 免责声明
  4. 本研究报告不构成投资建议或推荐。所有投资存在风险,包括本金损失。
  5. 重要提示:
  6. 1. 本报告仅供教育和信息用途
  7. 2. 部分数据需要通过官方渠道验证
  8. 3. 过往业绩不代表未来表现
  9. 4. 投资决策前请自行进行尽职调查
  10. 5. 建议咨询合格的财务顾问
  11. ---
  12. 🎓 研究框架
  13. 本研究基于 Claude Code Deep Research 系统:
  14. - 方法论: 8阶段股票投资尽调框架
  15. - 智能体: 28个并行研究智能体
  16. - 工具: WebSearch、WebFetch、综合分析
  17. - 质量: 多空平衡、明确风险、数据验证
  18. ---
  19. ## Table of Contents
  20. 1. [Features](#features)
  21. 2. [Repo Structure](#repo-structure)
  22. 3. [Quick Start](#quick-start)
  23. 4. [Stock Investment Research](#stock-investment-research)
  24. 5. [How It Works](#how-it-works)
  25. 6. [Customization](#customization)
  26. 7. [Credits & Acknowledgements](#credits--acknowledgements)
  27. 8. [License](#license)
  28. ---
  29. ## Features
  30. This repository contains **two specialized deep research frameworks** for Claude Code:
  31. ### 1. 🎯 Stock Investment Research (股票投资尽调系统) ⭐ PRIMARY
  32. An **8-phase investment due diligence framework** for analyzing publicly traded companies, inspired by professional investment research methodologies.
  33. **Key Capabilities**:
  34. - 📊 **Comprehensive Analysis**: Business model, industry dynamics, financial quality, governance, valuation
  35. - 🤖 **Multi-Agent Research**: ~28 parallel research agents working concurrently
  36. - 📈 **Investment Style Adaptation**: Value, growth, turnaround, dividend investing
  37. - 💰 **Valuation Models**: DCF, reverse DCF, relative valuation, scenario analysis
  38. - 🛡️ **Risk Assessment**: Bear case, black swans, monitoring checklist
  39. - ✅ **Quality Assurance**: Cross-validation (profit vs. cash flow, company vs. peers)
  40. - 📝 **Structured Output**: 20-file standardized due diligence report
  41. **Research Coverage**:
  42. - A-shares (A股) - 中国大陆股市
  43. - Hong Kong stocks (港股)
  44. - US stocks (美股)
  45. - Other global markets
  46. **Output**: Signal rating (🟢🟢🟢 Strong Buy / 🟡🟡🟡 Hold / 🔴🔴 Avoid) based on fundamental analysis
  47. ### 2. 📚 General Deep Research (通用深度研究系统)
  48. A flexible **7-phase framework** for general research topics (business, technology, academic, etc.).
  49. ---
  50. ## Repo Structure
  51. | File/Folder | Purpose |
  52. |-------------|---------|
  53. | **CLAUDE.md** | Master instructions for Claude Code |
  54. | **.claude/skills/stock-question-refiner/** | Stock research question refinement skill |
  55. | **.claude/skills/stock-research-executor/** | 8-phase investment due diligence executor |
  56. | **.claude/commands/stock-research.md** | Main stock research command |
  57. | **.claude/skills/citation-validator/** | Citation verification skill |
  58. | **.claude/skills/got-controller/** | Graph of Thoughts controller |
  59. | **.claude/skills/synthesizer/** | Findings synthesis skill |
  60. | **STOCK_RESEARCH_IMPLEMENTATION_PLAN.md** | Stock research system design document |
  61. | **CLAUDE2.md** | Graph of Thoughts implementation details |
  62. | **PROJECT_UNDERSTANDING.md** | Architecture deep dive |
  63. | **IMPLEMENTATION_GUIDE.md** | User guide |
  64. ---
  65. ## Quick Start
  66. ### Stock Research (股票投资尽调)
  67. ```bash
  68. # Start Claude Code
  69. claude
  70. # Set model (optional, but recommended)
  71. /model opus
  72. # Execute stock research
  73. /stock-research [股票代码或公司名称]
  74. # Examples:
  75. /stock-research 600519 # 贵州茅台 (A-share)
  76. /stock-research AAPL # 苹果公司 (US)
  77. /stock-research 腾讯 00700.HK # 腾讯控股 (HK)
  78. ```
  79. **The system will**:
  80. 1. Ask about your investment style (价值/成长/困境/红利), holding period, risk tolerance
  81. 2. Deploy ~28 parallel research agents across 7 phases
  82. 3. Generate comprehensive due diligence report in `RESEARCH/STOCK_[ticker]_[company]/`
  83. **Time**: 2-4 hours for standard due diligence
  84. ### Output Example
  85. ```
  86. RESEARCH/STOCK_600519_Kweichow_Moutai/
  87. ├── 00_Executive_Summary.md # 🟡🟡🟡 Hold / Fairly Valued
  88. ├── 01_Business_Foundation.md # Products, revenue, customers
  89. ├── 02_Industry_Analysis.md # Industry cycle, competition
  90. ├── 03_Business_Breakdown.md # Profit drivers, economics
  91. ├── 04_Financial_Quality.md # Cash flow, margins, red flags
  92. ├── 05_Governance_Analysis.md # Ownership, management
  93. ├── 06_Market_Sentiment.md # Bull/bear cases
  94. ├── 07_Valuation_Moat.md # Moat rating, valuation
  95. ├── Financial_Data/ # Metrics, trends, peer comparison
  96. ├── Valuation/ # DCF, scenarios
  97. ├── Risk_Monitoring/ # Bear case, monitoring checklist
  98. └── sources/ # Citations with quality ratings
  99. ```
  100. ---
  101. ## Stock Investment Research
  102. ### 8-Phase Due Diligence Process
  103. | Phase | Focus | Output |
  104. |-------|-------|--------|
  105. | **1. Business Foundation** | 公司事实底座 | Products, revenue mix, customers, value chain, strategy |
  106. | **2. Industry Analysis** | 行业周期分析 | Cycle stage, supply-demand, competition, policy impacts |
  107. | **3. Business Breakdown** | 业务拆解 | Segments, profit engines, pricing power, economics |
  108. | **4. Financial Quality** | 财务质量 | Metrics trends, cash flow vs. earnings, red flags, peers |
  109. | **5. Governance Analysis** | 股权治理 | Ownership, management, capital allocation, ROIC |
  110. | **6. Market Sentiment** | 市场分歧 | Bull case, bear case, key debates, verification nodes |
  111. | **7. Valuation & Moat** | 估值护城河 | Moat rating (0-5), relative/absolute valuation, risks |
  112. | **8. Final Synthesis** | 综合报告 | Signal rating, thesis, monitoring checklist |
  113. ### Investment Style Adaptation
  114. The system adapts research approach based on investment style:
  115. | Style | Focus | Valuation Methods | Key Metrics |
  116. |-------|-------|-------------------|-------------|
  117. | **Value** (价值投资) | Intrinsic value, margin of safety | P/B, EV/EBITDA, DCF (conservative) | P/B, normalized earnings, FCF yield |
  118. | **Growth** (成长投资) | TAM, competitive positioning | PEG, DCF (aggressive), user models | Revenue growth, moat, TAM penetration |
  119. | **Turnaround** (困境反转) | Liquidity, solvency, catalysts | Liquidation value, option value | Debt ratios, cash runway, catalyst timeline |
  120. | **Dividend** (红利投资) | Dividend sustainability | DDM, FCF yield, yield comparison | Dividend yield, payout ratio, FCF coverage |
  121. ### Quality Standards
  122. **Mandatory Cross-Validation**:
  123. - ✅ Profit vs. cash flow (OCF/NI ratio analysis)
  124. - ✅ Company vs. peer comparison (key ratios, margins)
  125. - ✅ Bear case analysis (3-5 key risks identified)
  126. **Citation Requirements**:
  127. - Every factual claim must include: Author, Date, Title, URL
  128. - Source quality rated (A-E scale)
  129. - A-grade sources: Annual reports, regulatory filings
  130. - B-grade: Industry reports, analyst research
  131. - C-grade: News articles, expert commentary
  132. **Signal Rating** (based on fundamentals only):
  133. - 🟢🟢🟢 **Strong Buy**: Significant margin of safety, strong moat, attractive valuation
  134. - 🟡🟡🟡 **Hold**: Fairly valued or limited margin of safety
  135. - 🔴🔴 **Avoid**: Overvalued, deteriorating fundamentals, excessive risks
  136. ### Example Usage
  137. ```
  138. User: /stock-research 贵州茅台 600519
  139. Claude: 我可以帮您研究贵州茅台。让我先了解您的投资需求:
  140. 1. 投资风格:价值投资/成长投资/困境反转/红利投资?
  141. 2. 持有周期:短期(<6月)/中期(6-18月)/长期(1-3年以上)?
  142. 3. 关注重点:生意质量/财务质量/估值/公司治理 (选2-3个)
  143. 4. 风险偏好:保守/平衡/激进?
  144. User: 价值投资,长期持有3年以上,关注:生意质量、公司治理、估值,风险保守
  145. Claude: [Generating research plan...]
  146. [Deploying 28 parallel research agents...]
  147. [Analyzing 5-10 years of financial data...]
  148. [Comparing with Wuliangye, Yanghe, Fenjiu...]
  149. [Assessing competitive moat...]
  150. [DCF valuation with 3 scenarios...]
  151. [Identifying bear case risks...]
  152. Output: RESEARCH/STOCK_600519_Kweichow_Moutai/
  153. 🟡🟡🟡 Hold / Fairly Valued
  154. Investment Thesis:
  155. 茅台是中国领先的白酒品牌,拥有强大的品牌护城河和定价能力。然而当前估值(P/E 32x)安全边际有限。建议继续持有现有仓位,但新投资应等待10-15%回调至¥1,750-1,850区间。
  156. Key Metrics:
  157. - Market Cap: ¥2.8T
  158. - P/E (TTM): 32x (above 5-year average)
  159. - Gross Margin: 91.2%
  160. - ROE: 31%
  161. - Moat Rating: 5/5 (Very Strong)
  162. Top 3 Reasons to Consider:
  163. 1. Unassailable brand moat with 800-year heritage
  164. 2. Exceptional margins (91% gross, 53% net)
  165. 3. Strong cash generation (OCF/NI > 1.0)
  166. Top 3 Reasons to Avoid:
  167. 1. Full valuation (P/E 32x, limited margin of safety)
  168. 2. Regulatory risk (government scrutiny of luxury pricing)
  169. 3. Competitive intensification (Wuliangwa narrowing gap)
  170. Monitoring Checklist:
  171. ✅ Strengthen: Price pulls back 10-15% to ¥1,750-1,850
  172. ❌ Exit: Price drops below ¥1,300 (-35%), net margin < 45%
  173. [Full report: 20 files, 127 sources, 50+ pages]
  174. ```
  175. ---
  176. ## How It Works
  177. ### Stock Research Workflow
  178. ```
  179. User: /stock-research [ticker]
  180. ↓
  181. stock-question-refiner skill
  182. - Asks: Investment style? Holding period? Focus areas? Risk tolerance?
  183. ↓
  184. Structured Research Prompt (investment parameters, priorities, constraints)
  185. ↓
  186. stock-research-executor skill
  187. ├─ Phase 1: Business Foundation (4 parallel agents)
  188. ├─ Phase 2: Industry Analysis (4 parallel agents)
  189. ├─ Phase 3: Business Breakdown (4 parallel agents)
  190. ├─ Phase 4: Financial Quality (4 parallel agents)
  191. ├─ Phase 5: Governance Analysis (4 parallel agents)
  192. ├─ Phase 6: Market Sentiment (4 parallel agents)
  193. └─ Phase 7: Valuation & Moat (4 parallel agents)
  194. ↓
  195. citation-validator skill
  196. - Verifies all claims have citations
  197. - Rates source quality (A-E)
  198. ↓
  199. Comprehensive Investment Due Diligence Report
  200. - Signal rating
  201. - 8 phase reports
  202. - Financial data tables
  203. - Valuation analysis
  204. - Risk monitoring checklist
  205. ```
  206. ### Key Innovations
  207. 1. **Investment Style Adaptation**: Research approach tailored to value, growth, turnaround, or dividend investing
  208. 2. **Parallel Multi-Agent Execution**: ~28 agents working concurrently for efficiency
  209. 3. **Mandatory Cross-Validation**: Profit vs. cash flow, company vs. peers, bear case analysis
  210. 4. **Structured Output**: Standardized 20-file report format
  211. 5. **Quality Assurance**: A-E source quality rating, citation verification
  212. ### General Research Workflow (Secondary)
  213. ```
  214. [ Question ] → [ stock-question-refiner ]
  215. ↓
  216. [ Structured Prompt ]
  217. ↓
  218. [ research-executor ]
  219. ├─ Planning (break into subtopics)
  220. ├─ Multi-Agent Research (parallel)
  221. ├─ Source Triangulation (A-E rating)
  222. └─ Synthesis (combine findings)
  223. ↓
  224. [ Citation Validation ]
  225. ↓
  226. [ Research Report ]
  227. ```
  228. ---
  229. ## Customization
  230. ### Adapting Stock Research Parameters
  231. The system automatically adapts based on:
  232. 1. **Investment Style**:
  233. - Value: Emphasize balance sheet, normalized earnings, margin of safety
  234. - Growth: Emphasize TAM, competitive positioning, growth sustainability
  235. - Turnaround: Emphasize liquidity, solvency, catalysts
  236. - Dividend: Emphasize payout sustainability, FCF generation
  237. 2. **Holding Period**:
  238. - Short-term (<6 months): Focus on near-term catalysts, sentiment
  239. - Medium-term (6-18 months): Balanced approach
  240. - Long-term (1-3+ years): Emphasize business sustainability, moat, intrinsic value
  241. 3. **Risk Tolerance**:
  242. - Conservative: Add filters (debt limits, minimum profitability)
  243. - Balanced: Standard risk checks
  244. - Aggressive: Accept higher volatility, focus on upside scenarios
  245. ### Customizing Output
  246. Adjust research parameters by answering the question-refiner's questions with your specific needs:
  247. - Geographic focus (China, US, global)
  248. - Timeframe (3 years, 5 years, 10 years of data)
  249. - Source preferences (annual reports only, include news, etc.)
  250. - Language (Chinese, English, or bilingual)
  251. - Valuation methods (DCF required? sum-of-parts?)
  252. ---
  253. ## Credits & Acknowledgements
  254. ### Stock Research Framework
  255. - **8-Phase Methodology**: Based on professional investment due diligence best practices
  256. - **Graph of Thoughts Framework**: [SPCL, ETH Zürich](https://github.com/spcl/graph-of-thoughts) (MIT License)
  257. - **Quality Standards**: Inspired by institutional investment research processes
  258. ### Core System
  259. - **Research Methodology**: Inspired by OpenAI and Google Gemini deep research playbooks
  260. - **Prompt Generation**: Eliminates need for external question-refinement tools
  261. - **Claude Code Integration**: Leverages native Skills and Commands capabilities
  262. ### Development
  263. - **Developed by**: Ankit at [My Business Care Team (MyBCAT)](https://mybcat.com)
  264. - **Stock Research Edition**: December 2025
  265. - **License**: MIT License (see LICENSE file)
  266. ---
  267. ## License
  268. MIT License. See `LICENSE` file for full details.
  269. ---
  270. ## Important Disclaimer
  271. ⚠️ **WARNING / 重要提示**:
  272. **Stock Research System**:
  273. - This system does **NOT** provide investment advice
  274. - This system does **NOT** predict stock prices or provide target prices
  275. - Signal ratings (🟢🟢🟢/🟡🟡🟡/🔴🔴) are based **ONLY on fundamental analysis** (business quality, financial health, valuation, competitive moat)
  276. - All investments involve risk, including the loss of principal
  277. - Past performance does not guarantee future results
  278. - Always conduct your own due diligence and consult with qualified financial advisors before making investment decisions
  279. **股票研究系统**:
  280. - 本系统**不构成投资建议**
  281. - 本系统**不预测股价**
  282. - 信号灯评级仅基于**基本面分析**(业务质量、财务健康、估值、护城河)
  283. - 所有投资均有风险,包括本金损失
  284. - 过往表现不代表未来结果
  285. - 请自行进行尽职调查并在做出投资决策前咨询合格的财务顾问
  286. - 提示词参考来源:https://mp.weixin.qq.com/s/EFT5S-cCeCnEIDZOD_DYbA
  287. ---
  288. ## Support
  289. For detailed documentation:
  290. - See `CLAUDE.md` for Claude Code instructions
  291. - See `STOCK_RESEARCH_IMPLEMENTATION_PLAN.md` for system design
  292. - See `.claude/skills/*/` for skill-specific instructions

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.