What problem does it solve? Generic AI financial analysis relies on secondhand summaries and produces vague, non-committal conclusions. This Skill performs deep earnings report analysis directly from primary sources (10-K filings, annual reports, earnings call transcripts), extracting verified financial data, tracking management promises, and forcing clear investment conclusions. ## Core Features & Use Cases - Primary Source Analysis: Retrieves original filings from SEC EDGAR, HKEX, and company IR pages, with an A/B/C source-availability rating that adjusts analysis depth accordingly. - Financial Data Verification: Cross-validates revenue, market cap, and valuation metrics across multiple sources using the financial_rigor.py tool, flagging discrepancies over 1%. - Management Tone & Promise Tracking: Analyzes earnings call language for candor or evasion signals and compares prior management commitments against actual results. - Footnote Mining: Checks related-party transactions, dilution, contingent liabilities, and accounting policy changes, plus anomaly detection like receivables growing faster than revenue. - Use Case: Ask for an earnings review of "Tencent 2025Q4" and receive a structured report covering core financials, management tone, hidden footnote risks, and a definitive verdict on whether the quarter strengthens or weakens the investment thesis. ## Quick Start Ask the AI to run an earnings review on a company and period, for example: run an earnings review of PDD's latest annual report using primary sources.
