Document Classification
Classify financial PDFs by extracting company identity, document type, and date metadata. Validates ticker via Yahoo Finance with multi-step fallback. Uses a Python orchestration script for validation, file modification, and writing markdown.
Financial Data Extraction
Extract balance sheet, income statement, shares outstanding, organic growth, and GAAP reconciliation data from financial PDFs. Standardize via Tiger-Transformer and append structured output to the document markdown.
Qualitative Assessment
Assess a company's economic moat, EBITA margin trajectory, and organic growth trajectory from analyst reports, earnings transcripts, or long-form articles. Produces structured qualitative outlook that feeds into the Financial Modeling skill's assumption generation.
Document Organization
Execute a single deterministic Python script to harmonize units, create/update metadata, move files to output_data/, and clean up input_data/.
Financial Modeling
Execute a single deterministic Python script to compute WACC, DCF assumptions, projected free cash flows, enterprise value, and intrinsic value per share. Updates the metadata markdown.
Financial Calculations
Execute a single deterministic Python script to compute all derived financial metrics (EBITA, Invested Capital, Tax Rates, Summary Table) from extracted financial data.
Model JSON Generator
Extracts the WACC, assumptions, and DCF projections from the markdown metadata file and converts them into a clean, structured JSON file for the frontend interactive viewer.