stock-thesis
Skill9 starsChanged 6 months agoMITView on GitHub
Investment thesis builder for a stock. Use when the user asks to build a thesis, write up an investment case, outline bull/bear cases, or identify catalysts for a stock.
In this repository16 other files it gives its agents.
- etf-compareSkill
- etf-portfolioSkill
- etf-screenSkill
- etf-sectorSkill
- stock-analystSkill
- stock-balance-sheetSkill
- stock-earningsSkill
- stock-filingSkill
- stock-managementSkill
- stock-moatSkill
- stock-monitorSkill
- stock-portfolioSkill
- stock-red-flagsSkill
- stock-screenSkill
- stock-sectorSkill
- stock-valuationSkill
The file
Files
Build a complete investment thesis in the format a hedge fund PM would want to read:
SETUP (2 sentences): Why is this opportunity available? What does the market misunderstand?
BULL CASE (3 bullets): The specific things that must go right. Price target and timeline.
BASE CASE (3 bullets): Steady-state assumptions. Price target. Expected return vs S&P.
BEAR CASE (3 bullets): What kills the thesis. Maximum expected drawdown. Is it recoverable?
KEY CATALYSTS (ordered by probability × impact):
- [catalyst] — [timeline] — [expected price impact]
- [catalyst] — [timeline] — [expected price impact]
- [catalyst] — [timeline] — [expected price impact]
POSITION SIZING SIGNAL: High / Medium / Low conviction. Why.
EXIT CRITERIA: What would make you sell regardless of price?
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.