Skip to content
Get packs

Investment Research Framework

Runs a structured, four-master (Buffett/Munger/Duan/Li Lu) investment research workflow on a company

Source Download skill
Repository
xbtlin/ai-berkshire
Stars
16,982
Licence
MIT
Files
1 file

What it does

This skill tells an AI agent to research a listed company in a fixed seven-step order: data collection, business quality, moat, risk review, management, industry trends, and valuation. It asks the agent to date-stamp its data, cross-check figures from multiple sources, and run calculations through bundled Python tools rather than guessing. The output is a written investment report that labels uncertainty and states how much weight the conclusion deserves.

Great for

  • Investors or students who want a disciplined, checklist-style research report on a stock
  • Analysts who want an AI to cross-check market cap, revenue and valuation figures before writing
  • People comfortable reviewing AI output critically before acting on it

Skip it if

  • Making buy or sell decisions without independent verification: the skill itself warns that AI research can echo market consensus or fill data gaps with plausible guesses
  • Users who expect real-time market data: the skill relies on web collection and the agent's own sources, which may be incomplete or wrong
  • Anyone needing personalised financial advice; this is a research workflow, not a licensed advisory service

Try asking

  • “Research Kweichow Moutai (600519) using the four-master framework and give me a report”
  • “Run a full investment analysis on a Hong Kong-listed tech company and cross-check its revenue”
  • “Evaluate the moat and management of a US-listed company and value it with three scenarios”
Step-by-step guide: how to use Investment Research FrameworkInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    investment-research.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip investment-research.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip investment-research.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give a precise company name or ticket symbol so the agent collects data for the right entity and exchange.
  • Check the data cutoff date and source list in the report header, and verify key figures against the company's own filings before relying on them.
  • Treat the valuation output as a stress test, not a verdict; ask the agent to show the discount-rate and growth assumptions it chose.

What's inside

  • SKILL.md

Redistributed unmodified from xbtlin/ai-berkshire under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.