financial-report-analyzer

Financial Report Analyzer Skill

This skill is designed to help DB-GPT systematically analyze listed company financial reports, producing high-quality financial analysis reports by extracting core data, calculating financial ratios, generating visualization charts, and combining business background.

Core Workflow

1. Data Extraction and Structuring：

   • Use the execute_skill_script_file tool to execute the scripts/extract_financials.py script, passing in the financial report file path (file_path parameter), to automatically extract core values such as revenue, net profit, assets, and liabilities.
   • The script supports PDF files (parsed via pdfplumber) and plain text files, returning structured data in JSON format.

2. Financial Ratio Calculation：

   • Use execute_skill_script_file to execute scripts/calculate_ratios.py, passing in the JSON data from Step 1.
   • Automatically calculate key indicators such as gross margin, net margin, ROE, and debt-to-asset ratio, and output 30 template placeholder key-value pairs.
   • Refer to references/financial_metrics.md to ensure the accuracy of indicator definitions.
   • The system will automatically save the returned JSON results（react_state["ratio_data"]), and the subsequent html_interpreter will automatically merge them.

1. Chart Generation：

   • Use execute_skill_script_file to execute scripts/generate_charts.py, passing in the JSON data from Step 1.
   • Automatically generate 3 visualization charts:
     • financial_overview.png: bar chart comparing core financial indicators
     • profitability.png: horizontal bar chart of profitability indicators
     • asset_structure.png: donut chart of asset structure
   • The system will automatically copy the images to the static directory and record the URL mapping（react_state["image_url_map"]), and the subsequent html_interpreter will automatically merge them.

2. In-Depth Analysis：

   • Follow the framework provided by references/analysis_framework.md to conduct in-depth analysis from the four dimensions of earnings quality, solvency risk, operating efficiency, and cash flow.
   • Combine with the "Management Discussion and Analysis" section to explain the core drivers of performance changes.
   • Write the following 7 sections of analysis text:
     • PROFITABILITY_ANALYSIS: Profitability Analysis
     • SOLVENCY_ANALYSIS: Solvency and Risk Analysis
     • EFFICIENCY_ANALYSIS: Operating Efficiency Analysis
     • CASHFLOW_ANALYSIS: Cash Flow and Profit Quality Analysis
     • ADVANTAGES_LIST: Core Strengths List (HTML <li> format)
     • RISKS_LIST: Major Risks List (HTML <li> format)
     • OVERALL_ASSESSMENT: Overall Assessment

3. Render Report：

   • Call html_interpreter, using the template_path mode:

     {
       "template_path": "financial-report-analyzer/templates/report_template.html",
       "data": {
         "PROFITABILITY_ANALYSIS": "LLM撰写的盈利能力分析...",
         "SOLVENCY_ANALYSIS": "LLM撰写的偿债分析...",
         "EFFICIENCY_ANALYSIS": "LLM撰写的营运效率分析...",
         "CASHFLOW_ANALYSIS": "LLM撰写的现金流分析...",
         "ADVANTAGES_LIST": "<li>优势1</li><li>优势2</li>",
         "RISKS_LIST": "<li>风险1</li><li>风险2</li>",
         "OVERALL_ASSESSMENT": "LLM撰写的综合评价..."
       },
       "title": "XX公司 2023年度财报分析报告"
     }
     

   • Important：data In the dictionary, you only need to pass in the 7 sections of analysis text you wrote! The backend will automatically merge:
     • The 30 data indicators from Step 2 (COMPANY_NAME, REVENUE, NET_PROFIT, etc.)
     • The chart URLs from Step 3 (CHART_FINANCIAL_OVERVIEW, CHART_PROFITABILITY, CHART_ASSET_STRUCTURE)
   • Absolutely do notinclude data indicators or chart paths in data , otherwise the JSON will be too large and cause truncation.

4. Done：

   • Call terminate to return a brief summary of 1-2 sentences.
   • Reports will be displayed as cards in the left panel; users can click a card to view the full report in the right panel.

Complete workflow example

Step 1: execute_skill_script_file(skill_name="financial-report-analyzer", script_file_name="extract_financials.py", args={"file_path": "/path/to/report.pdf"})
  → 返回 JSON: {"revenue": 10500000000, "net_profit": 1200000000, ...}  （记为 raw_data）

Step 2: execute_skill_script_file(skill_name="financial-report-analyzer", script_file_name="calculate_ratios.py", args=<raw_data>)
  → 返回 30 个模板键值，系统自动记录到 react_state["ratio_data"]

Step 3: execute_skill_script_file(skill_name="financial-report-analyzer", script_file_name="generate_charts.py", args=<raw_data>)
  → 生成图表，系统自动复制到 /images/ 并记录 URL 映射

Step 4: （LLM 自行撰写 7 段深度分析文本）

Step 5: html_interpreter(template_path="financial-report-analyzer/templates/report_template.html", data={仅包含 7 段分析文本}, title="报告标题")
  → 后端自动合并数据指标 + 图表 URL + 分析文本，渲染完整报告

Step 6: terminate(result="简短摘要")

Resource usage instructions

• Scripts(all executed via execute_skill_script_file ):
  • scripts/extract_financials.py: receives the file_path parameter, reads the financial report file (supports PDF and text formats), and extracts core financial data.
  • scripts/calculate_ratios.py: calculates financial ratios and outputs 30 template placeholder key-value pairs. The system automatically records the results.
  • scripts/generate_charts.py: generates 3 visualization charts (matplotlib); the system automatically handles image copying.
  • scripts/fill_template.py: (backup) receives the ratio_data、chart_paths、analysis three parameters, reads the HTML template, and replaces all placeholders. Under normal circumstances this script does not need to be used, because the template_path mode of html_interpreter automatically completes template filling.
• Reference：
  • references/financial_metrics.md: contains formula definitions.
  • references/analysis_framework.md: contains the analysis logic.
• Template：
  • templates/report_template.html: the HTML template for the final delivered report (must strictly follow, and sections must not be deleted or table structures modified). It is automatically read and filled by the template_path parameter of html_interpreter.
  • templates/report_template.md: Markdown version, for reference only as a structural explanation.

Notes

• Must use execute_skill_script_file to execute scripts (do not use shell_interpreter), because execute_skill_script_file automatically handles image copying and data recording.
• Script extraction may be affected by formatting; it is recommended to manually verify the key extracted values before calculation.
• Always pay attention to "non-recurring gains and losses" to assess the true profitability of the company's core business.
• Compare historical data for at least three years to identify trends.
• generate_charts.py depends on matplotlib; please ensure that this library is installed in the environment.