Back to Details

us-stock-researcher

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

US Stock Researcher

美股研究员

Institutional-grade deep analysis of US stock SEC filings, outputting professional investment reports.
针对美股SEC filings（美国证券交易委员会文件）的机构级深度分析，输出专业投资报告。

Research Mode Selection

研究模式选择

ModeWhen to UseRequirements
Gemini ModeDefault when GEMINI_API_KEY is configuredGEMINI_API_KEY environment variable
Claude Native ModeWhen no Gemini API or user requestsWebSearch tool access
模式适用场景要求
Gemini模式配置GEMINI_API_KEY时的默认模式GEMINI_API_KEY环境变量
Claude原生模式无Gemini API或用户要求时使用可访问WebSearch工具

Quick Start Workflow

快速开始流程

Step 1: Determine Filing Period

步骤1：确定报告周期

If user did NOT specify a period, use WebSearch to find the latest filing:
WebSearch: "{company_name} latest 10-K 10-Q SEC filing"
IMPORTANT: Always analyze the MOST RECENT filing by date, regardless of type (10-K or 10-Q).
Example decision logic:
  • If latest 10-K is 2024-12-31 and latest 10-Q is 2025-09-30 → Use 10-Q (more recent)
  • If latest 10-K is 2025-01-15 and latest 10-Q is 2024-09-30 → Use 10-K (more recent)
Inform user: "根据搜索，{TICKER} 最新的财报是 {10-K/10-Q}（截至 {period}），将分析该期财报"
如果用户未指定周期，使用WebSearch查找最新文件：
WebSearch: "{company_name} latest 10-K 10-Q SEC filing"
重要提示：无论报告类型是10-K还是10-Q，始终分析日期最新的文件。
示例决策逻辑：
  • 若最新10-K为2024-12-31，最新10-Q为2025-09-30 → 使用10-Q（更新）
  • 若最新10-K为2025-01-15，最新10-Q为2024-09-30 → 使用10-K（更新）
告知用户："根据搜索，{TICKER} 最新的财报是 {10-K/10-Q}（截至 {period}），将分析该期财报"

Step 2: Download Filing

步骤2：下载文件

bash
python3.11 scripts/download_sec_filings.py --ticker <TICKER> --type <10-K|10-Q|6-K> --limit 1
Output: 
<project_root>/investment-research/{TICKER}/tmp/sec_filings/cleaned.txt
bash
python3.11 scripts/download_sec_filings.py --ticker <TICKER> --type <10-K|10-Q|6-K> --limit 1
输出：
<project_root>/investment-research/{TICKER}/tmp/sec_filings/cleaned.txt

Step 3: Dynamic Framework Generation

步骤3：动态生成分析框架

  1. Read first 5000 characters of filing
  2. Identify company industry
  3. Select modules from 
    industry-analysis-modules.md
  4. Merge with 
    financial-analysis-framework.md
  5. Save to 
    tmp/analysis-framework-YYYY-MM-DD.md
  1. 读取文件前5000个字符
  2. 识别公司所属行业
  3. 从
    industry-analysis-modules.md
    中选择模块
  4. 与
    financial-analysis-framework.md
    合并
  5. 保存至
    tmp/analysis-framework-YYYY-MM-DD.md

Step 4: Execute Deep Research

步骤4：执行深度研究

Gemini Mode:
bash
python3.11 scripts/gemini_deep_research.py \
  --input <cleaned.txt path> \
  --prompt <analysis framework path> \
  --output-dir <project_root>/investment-research/<TICKER> \
  --ticker <TICKER> \
  --company <Company Name> \
  --phase all
Claude Native Mode: Follow 
prompts/claude-deep-research-protocol.md
for complete 7-phase execution.
Gemini模式：
bash
python3.11 scripts/gemini_deep_research.py \
  --input <cleaned.txt path> \
  --prompt <analysis framework path> \
  --output-dir <project_root>/investment-research/<TICKER> \
  --ticker <TICKER> \
  --company <Company Name> \
  --phase all
Claude原生模式： 遵循
prompts/claude-deep-research-protocol.md
完成7阶段执行。

Step 5: Format and Save

步骤5：格式化并保存

Format per 
markdown-formatter-rules.md
, save to 
investment-research/{TICKER}/
按照
markdown-formatter-rules.md
进行格式化，保存至
investment-research/{TICKER}/

Mode 1: Gemini Deep Research

模式1：Gemini深度研究

User Input → Download Filing → Framework Generation → Phase 1 Filing Analysis → Phase 2 Web Research → Integration → Final Report
                                                              ↓                         ↓
                                                      (Gemini Deep Research)    (Gemini Deep Research)
  • Phase 1: Upload filing via Files API, Gemini analyzes comprehensively
  • Phase 2: Web search for competitors, trends, management verification
  • Integration: Claude merges Phase 1 + Phase 2 per 
    prompts/report-merge-prompt.md
用户输入 → 下载文件 → 生成框架 → 阶段1 文件分析 → 阶段2 网络研究 → 整合 → 最终报告
                                                              ↓                         ↓
                                                      (Gemini深度研究)    (Gemini深度研究)
  • 阶段1：通过Files API上传文件，Gemini进行全面分析
  • 阶段2：网络搜索竞争对手、行业趋势、管理层信息验证
  • 整合：Claude按照
    prompts/report-merge-prompt.md
    合并阶段1和阶段2的结果

Mode 2: Claude Native Deep Research

模式2：Claude原生深度研究

Uses 7-Phase Deep Research + Graph of Thoughts (GoT) methodology.
For complete execution details, see: 
prompts/claude-deep-research-protocol.md
采用**7阶段深度研究+思维图（GoT）**方法论。
完整执行细节请参考： 
prompts/claude-deep-research-protocol.md

7-Phase Overview

7阶段概述

PhaseNameDescription
1Question ScopingDefine goals, download filing
2Retrieval PlanningIdentify industry, create research plan
3Iterative QueryingGoT branches: Financial, Competitive, Industry, Management, Risk
4Source TriangulationCross-validate findings
5Knowledge SynthesisStructure report per framework
6Quality AssuranceChain-of-Verification
7Output PackagingFormat and save
阶段名称描述
1问题界定定义目标，下载文件
2检索规划识别行业，制定研究计划
3迭代查询GoT分支：财务、竞争、行业、管理层、风险
4来源三角验证交叉验证研究结果
5知识整合按照框架结构化报告
6质量保证验证链（Chain-of-Verification）
7输出打包格式化并保存

GoT Research Branches

GoT研究分支

BranchMethodFocus
ARead filingFinancial data analysis
BWebSearchCompetitive landscape
CWebSearchIndustry trends
DWebSearchManagement verification
EWebSearchRisk factors
分支方法重点
A读取文件财务数据分析
BWebSearch竞争格局
CWebSearch行业趋势
DWebSearch管理层信息验证
EWebSearch风险因素

Reference Documents

参考文档

DocumentPurpose
financial-analysis-framework.mdBase analysis framework
industry-analysis-modules.mdIndustry-specific modules
markdown-formatter-rules.mdReport formatting rules
prompts/claude-deep-research-protocol.mdClaude Native 7-phase guide
prompts/report-merge-prompt.mdGemini mode report integration
文档用途
financial-analysis-framework.md基础分析框架
industry-analysis-modules.md行业特定模块
markdown-formatter-rules.md报告格式化规则
prompts/claude-deep-research-protocol.mdClaude原生7阶段指南
prompts/report-merge-prompt.mdGemini模式报告整合提示词

Output Location

输出位置

<project_root>/investment-research/{TICKER}/
├── tmp/
│   ├── sec_filings/cleaned.txt
│   ├── analysis-framework-YYYY-MM-DD.md
│   ├── phase1-YYYY-MM-DD.md
│   └── phase2-YYYY-MM-DD.md
└── {TICKER}-Investment-Report-YYYY-MM-DD.md
<project_root>/investment-research/{TICKER}/
├── tmp/
│   ├── sec_filings/cleaned.txt
│   ├── analysis-framework-YYYY-MM-DD.md
│   ├── phase1-YYYY-MM-DD.md
│   └── phase2-YYYY-MM-DD.md
└── {TICKER}-Investment-Report-YYYY-MM-DD.md

Usage Examples

使用示例

  • "Analyze AAPL's latest 10-K annual report"
  • "Deep research MSFT's 10-K filing"
  • "Analyze JPM's latest annual report" (auto-selects Financial module)
  • "Research PFE's financial report" (auto-selects Pharma module)
  • "分析AAPL最新的10-K年度报告"
  • "深度研究MSFT的10-K文件"
  • "分析JPM最新的年度报告"（自动选择金融模块）
  • "研究PFE的财务报告"（自动选择制药模块）