by liangdabiao
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
# Add to your Claude Code skills
git clone https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-AgentGuides for using ai agents skills like Claude-Code-Stock-Deep-Research-Agent.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T06:47:20.846Z",
"semgrepRan": false,
"npmAuditRan": true,
"pipAuditRan": true
}Claude-Code-Stock-Deep-Research-Agent is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by liangdabiao. 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. It has 349 GitHub stars.
Yes. Claude-Code-Stock-Deep-Research-Agent passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Claude-Code-Stock-Deep-Research-Agent against similar tools.
No comments yet. Be the first to share your thoughts!
Investment Research Edition - 专业股票投资尽调系统
⚖️ 免责声明
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。
重要提示:
🎓 研究框架
本研究基于 Claude Code Deep Research 系统:
This repository contains two specialized deep research frameworks for Claude Code:
An 8-phase investment due diligence framework for analyzing publicly traded companies, inspired by professional investment research methodologies.
Key Capabilities:
Research Coverage:
Output: Signal rating (🟢🟢🟢 Strong Buy / 🟡🟡🟡 Hold / 🔴🔴 Avoid) based on fundamental analysis
A flexible 7-phase framework for general research topics (business, technology, academic, etc.).
| File/Folder | Purpose |
|---|---|
| CLAUDE.md | Master instructions for Claude Code |
| .claude/skills/stock-question-refiner/ | Stock research question refinement skill |
| .claude/skills/stock-research-executor/ | 8-phase investment due diligence executor |
| .claude/commands/stock-research.md | Main stock research command |
| .claude/skills/citation-validator/ | Citation verification skill |
| .claude/skills/got-controller/ | Graph of Thoughts controller |
| .claude/skills/synthesizer/ | Findings synthesis skill |
| STOCK_RESEARCH_IMPLEMENTATION_PLAN.md | Stock research system design document |
| CLAUDE2.md | Graph of Thoughts implementation details |
| PROJECT_UNDERSTANDING.md | Architecture deep dive |
| IMPLEMENTATION_GUIDE.md | User guide |
# 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:
RESEARCH/STOCK_[ticker]_[company]/Time: 2-4 hours for standard due diligence
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
| Phase | Focus | Output |
|---|---|---|
| 1. Business Foundation | 公司事实底座 | Products, revenue mix, customers, value chain, strategy |
| 2. Industry Analysis | 行业周期分析 | Cycle stage, supply-demand, competition, policy impacts |
| 3. Business Breakdown | 业务拆解 | Segments, profit engines, pricing power, economics |
| 4. Financial Quality | 财务质量 | Metrics trends, cash flow vs. earnings, red flags, peers |
| 5. Governance Analysis | 股权治理 | Ownership, management, capital allocation, ROIC |
| 6. Market Sentiment | 市场分歧 | Bull case, bear case, key debates, verification nodes |
| 7. Valuation & Moat | 估值护城河 | Moat rating (0-5), relative/absolute valuation, risks |
| 8. Final Synthesis | 综合报告 | Signal rating, thesis, monitoring checklist |
The system adapts research approach based on investment style:
| Style | Focus | Valuation Methods | Key Metrics |
|---|---|---|---|
| Value (价值投资) | Intrinsic value, margin of safety | P/B, EV/EBITDA, DCF (conservative) | P/B, normalized earnings, FCF yield |
| Growth (成长投资) | TAM, competitive positioning | PEG, DCF (aggressive), user models | Revenue growth, moat, TAM penetration |
| Turnaround (困境反转) | Liquidity, solvency, catalysts | Liquidation value, option value | Debt ratios, cash runway, catalyst timeline |
| Dividend (红利投资) | Dividend sustainability | DDM, FCF yield, yield comparison | Dividend yield, payout ratio, FCF coverage |
Mandatory Cross-Validation:
Citation Requirements:
Signal Rating (based on fundamentals only):
User: /stock-research 贵州茅台 600519
Claude: 我可以帮您研究贵州茅台。让我先了解您的投资需求:
1. 投资风格:价值投资/成长投资/困境反转/红利投资?
2. 持有周期:短期(<6月)/中期(6-18月)/长期(1-3年以上)?
3. 关注重点:生意质量/财务质量/估值/公司治理 (选2-3个)
4. 风险偏好:保守/平衡/激进?
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
Claude: [Generating research plan...]
[Deploying 28 parallel research agents...]
[Analyzing 5-10 years of financial data...]
[Comparing with Wuliangye, Yanghe, Fenjiu...]
[Assessing competitive moat...]
[DCF valuation with 3 scenarios...]
[Identifying bear case risks...]
Output: RESEARCH/STOCK_600519_Kweichow_Moutai/
🟡🟡🟡 Hold / Fairly Valued
Investment Thesis:
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。
Key Metrics:
- Market Cap: ¥2.8T
- P/E (TTM): 32x (above 5-year average)
- Gross Margin: 91.2%
- ROE: 31%
- Moat Rating: 5/5 (Very Strong)
Top 3 Reasons to Consider:
1. Unassailable brand moat with 800-year heritage
2. Exceptional margins (91% gross, 53% net)
3. Strong cash generation (OCF/NI > 1.0)
Top 3 Reasons to Avoid:
1. Full valuation (P/E 32x, limited margin of safety)
2. Regulatory risk (government scrutiny of luxury pricing)
3. Competitive intensification (Wuliangwa narrowing gap)
Monitoring Checklist:
✅ Strengthen: Price pulls back 10-15% to ¥1,750-1,850
❌ Exit: Price drops below ¥1,300 (-35%), net margin < 45%
[Full report: 20 files, 127 sources, 50+ pages]
User: /stock-research [ticker]
↓
stock-question-refiner skill
- Asks: Investment style? Holding period? Focus areas? Risk tolerance?
↓
Structured Research Prompt (investment parameters, priorities, constraints)
↓
stock-research-executor skill
├─ Phase 1: Business Foundation (4 parallel agents)
├─ Phase 2: Industry Analysis (4 parallel agents)
├─ Phase 3: Business Breakdown (4 parallel agents)
├─ Phase 4: Financial Quality (4 parallel agents)
├─ Phase 5: Governance Analysis (4 parallel agents)
├─ Phase 6: Market Sentiment (4 parallel agents)
└─ Phase 7: Valuation & Moat (4 parallel agents)
↓
citation-validator skill
- Verifies all claims have citations
- Rates source quality (A-E)
↓
Comprehensive Investment Due Diligence Report
- Signal rating
- 8 phase reports
- Financial data tables
- Valuation analysis
- Risk monitoring checklist
[ Question ] → [ stock-question-refiner ]
↓
[ Structured Prompt ]
↓
[ research-executor ]
├─ Planning (break into subtopics)
├─ Multi-Agent Research (parallel)
├─ Source Triangulation (A-E rating)
└─ Synthesis (combine findings)
↓
[ Citation Validation ]
↓
[ Research Report ]
The system automatical