xbtlin/ai-berkshire

This page introduces an external open-source repository. It is not an HDATF product.

What it does

Investment research skills for Claude Code and Codex that structure the methods of four value investors. Multiple agents research in parallel and challenge each other, and reports must end in a clear pass, fail or gray-zone verdict.

How it helps ATF

Outside our domain. Its pattern of forcing a clear verdict and having agents challenge each other's analysis could be loosely worth comparing for the report step in LabChin.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

• zhaoxuya520/reverse-skill
  A skill router pack for AI coding clients like Claude Code and Cursor, covering reverse engineering, authorized penetration testing and security research. It routes each task to a methodology, checks available tools and records evidence, findings and past lessons.
• DietrichGebert/ponytail
  A skill for AI coding agents such as Claude Code that pushes them to write as little code as possible instead of over-building. The readme reports less code and lower cost than the same agent without the skill.
• emilkowalski/skills
  A set of agent skills for designers and engineers that list common mistakes agents make in interface animation and design, such as the wrong easing curve, and explain how to fix them.
• shadcn/improve
  An agent skill that audits a codebase and writes self-contained implementation plans as markdown files for cheaper models to execute. The skill does not write code itself, and an execute mode dispatches a cheaper executor and reviews its work.
• ayghri/i-have-adhd
  A skill for coding agents that makes answers action-first. It sets rules such as leading with the next action, numbering steps, ending with one concrete next step, suppressing tangents and capping lists at five items.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.