mohnish-pabrai
Skill19 starsChanged 11 months agoMITView on GitHub
Analyze stocks using Mohnish Pabrai's Dhandho framework. Use when seeking low-risk, high-return opportunities with asymmetric payoffs.
In this repository20 other files it gives its agents.
- aswath-damodaranSkill
- ben-grahamSkill
- bill-ackmanSkill
- cathie-woodSkill
- charlie-mungerSkill
- financial-dataSkill
- fundamentalsSkill
- growth-analystSkill
- michael-burrySkill
- news-sentimentSkill
- peter-lynchSkill
- phil-fisherSkill
- portfolio-managerSkill
- rakesh-jhunjhunwalaSkill
- risk-managerSkill
- sentimentSkill
- stanley-druckenmillerSkill
- technicalsSkill
- valuationSkill
- warren-buffettSkill
The file
Files
Mohnish Pabrai Investment Analysis
Investment Philosophy (Dhandho)
- Dhandho: Heads I win, tails I don't lose much
- Low Risk, High Uncertainty: Exploit the difference
- Cloning: Copy successful investors
- Few Bets, Big Bets: Concentrate when odds favor you
- Simple Businesses: Easy to understand
Analysis Process
Run Pabrai Analysis
python .claude/skills/mohnish-pabrai/scripts/analyze.py {TICKER} {END_DATE}Dhandho Checklist
- Is the downside protected?
- Is the upside significant?
- Is the business simple to understand?
- Is there a moat?
- Is management owner-operator?
- Is the price compelling?
Key Criteria
- Asymmetric Risk/Reward: 3:1 or better
- Margin of Safety: Significant discount to value
- Simple Business: Understandable model
- Owner-Operators: Skin in the game
Signal Interpretation
- Bullish: Low downside, high upside, simple business
- Neutral: Mixed risk/reward profile
- Bearish: High risk or complex business
Example
Analyze AAPL as of 2024-12-01 using Pabrai's Dhandho framework.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

