This repository offers a collection of AI skills designed around Warren Buffett's investment framework, providing a systematic approach to stock analysis and investment evaluation. It aims to empower users with Buffett's time-tested principles for making informed financial decisions, from initial screening to deep dives into company reports and industry specifics.

How It Works

The buffett-skills project employs a progressive disclosure architecture. A core SKILL.md file is always loaded, with 8 supplementary reference files loaded on-demand based on the analysis type: quick screening, deep analysis, or specific topic questions. This dispatch logic ensures targeted information retrieval, leveraging structured data flow and systematic reading of reference materials compiled from Buffett's writings. The system prioritizes analytical depth and strict adherence to a comprehensive output format.

Quick Start & Requirements

• Primary install / run command: Clone the repository and copy the skills/buffett folder into your project's .claude/skills/buffett directory. Claude Code auto-discovers skills placed in this location.
• Non-default prerequisites and dependencies: Requires the Claude Code environment.
• Links: GitHub Repository

Highlighted Details

• Achieved a 100% pass rate across 3 benchmark test cases (Apple stock, banking framework, Moutai hold/sell), a significant improvement over a 66.7% rate without the skill.
• The skill's analytical depth comes at the cost of increased processing: average tokens increased by over 30,000 and average time by nearly a minute per analysis.
• Outputs a highly structured template including conclusion, key assumptions, business quality, financial snapshot, valuation, risks, and monitoring indicators.
• Reference files are derived from 49 concept pages within Buffett's shareholder letters and public writings.

Maintenance & Community

No specific information regarding maintainers, community channels (e.g., Discord/Slack), or roadmap is provided in the README.

Licensing & Compatibility

The README does not specify a software license. Users should verify licensing terms for compatibility with commercial or closed-source projects.

Limitations & Caveats

The primary trade-off for the enhanced analytical depth and structured output is a substantial increase in token usage and processing time. The skill is dependent on the Claude Code environment for its functionality and auto-discovery mechanism.