Stock Value Investment Analysis Assistant

Common Pitfalls in Value Investing Analysis

Investors frequently encounter specific issues when analyzing stocks: chaotic data sources where analyst price targets are confused with real-time prices; subjective frameworks lacking reproducible quantitative boundaries; over-reliance on single-year snapshots while ignoring 5-10 year trends; and emotional decision-making during market euphoria or panic.

How the Skill Works: A Dual-Layer Assessment Framework

The skill establishes a dual-layer assessment architecture, its core methodology. It provides an analytical scaffold rather than a simple "buy/sell" signal.

1. Data Acquisition and Verification Iron Rules
Before any analysis, the skill enforces a strict data protocol:
- API-First Principle: Data is fetched via a dual-engine script (fetch_stock_data.py) using yfinance + AkShare; web scraping is a last resort.
- Multi-Source Cross-Validation: Price data must be verified across at least 3 independent authoritative sources, each tagged with [Data Type / Timestamp / Currency].
- Source Tier Labeling: Every data point requires a label from T0 (API direct) to T5 (rumor). Weak sources (T4/T5) are prohibited for core scoring.
- Mandatory Time Series: Single-year snapshots are forbidden. Analysis must reference at least 5 years of time_series trend data.

2. Three-Dimensional Analysis Modules
Analysis unfolds across three indispensable dimensions, with module scores derived from qualitative frameworks, while quantitative models serve for calibration and vetoing:
- Industry Analysis (30% Weight): Assesses industry structure, pricing power, demand stability, and entry barriers.
- Company Analysis (35% Weight): The core focus includes qualitative moat assessment, a Financial Quality Scorecard (calculated via scripts using F-Score/M-Score), and management & capital allocation evaluation, all calibrated against time series trends.
- Price/Valuation Analysis (25% Weight): Employs quantitative models like Reverse DCF (inferring market-implied growth), EPV, and scenario weighting. It emphasizes "PE is a result, not a cause."

3. Contrarian Checks & Composite Scoring
The skill integrates contrarian investment checks (finding opportunities in panic) and a pricing power assessment. Finally, the company score (moat + financial quality + management) is combined with industry and valuation analysis to produce a composite rating (80-100), explicitly listing veto conditions such as ROE > 30% or a triggered M-Score.

Applicable Boundaries & Core Principles

Crucially, this skill is an analytical framework, not an investment advisor. Its methodology is derived from public works by investors like Philip Carret, but it doesn't represent their views. Clear boundaries apply:
- It does not predict short-term price movements or perform technical analysis.
- Quantitative models have limitations: They may return applicable=false for financial stocks or A-shares with insufficient data, requiring a shift to qualitative judgment rather than mechanical rejection.
- Outputs are not recommendations: All conclusions require independent user judgment, with profits and losses at the user's discretion.

Core principles are paramount: The three "goods" are non-negotiable (good industry, good company, good price); qualitative determines direction, quantitative sets boundaries; cheapness must be model-proven. Ultimately, know your circle of competence—if you don't understand it, stay away.