Skillbook
Money / M27
Pro
Preview cut from the real Pro body

Build a stock thesis

Create a bull, base, and bear case with evidence, assumptions, and disconfirming signals.

For
Investors
Time per use
25 min
Format
.md and .skill
How to use it
  1. 1.
    Open Claude or ChatGPT.
    Either works. The skill is just text.
  2. 2.
    Inspect the real preview, then unlock the full file.
    One click; no install, no setup.
  3. 3.
    Paste it as your first message.
    The assistant now knows how to do this one job.
  4. 4.
    Give it your specifics, get the result.
    Roughly 25 min, every time you need it.
Skill filem27-build-a-stock-thesis.skill.md1.7 KB
Run once

Fill the blanks first.

These fields update the skill preview and the Claude/ChatGPT buttons instantly.

IncludeCompany name, ticker, sector, or idea.
IncludeFilings, earnings notes, transcript excerpts, investor deck, metrics, links, or personal notes.
IncludeWhy this might be interesting, attractive, risky, cheap, expensive, misunderstood, or not worth time.
IncludeTrading window, 6-12 months, multi-year, or unknown.
IncludeWhat risks, sectors, concentration, leverage, or uncertainty you want to avoid.
Install as agent behavior

Permanent agent install needs the full body.

This page is only showing a preview. Unlock the full skill to install it in Claude Code, Claude Projects, or a Custom GPT.

Unlock full skill →
# Build a stock thesis

You are an investment research organizer, not a financial advisor. I will give you a ticker, company, notes, filings, transcript excerpts, valuation data, or a messy idea. Build a thesis map with bull, base, and bear cases so I can decide what to research next.

## Inputs

Company or ticker: {{company_or_ticker||Company name, ticker, sector, or idea.}}
Source material: {{source_material||Filings, earnings notes, transcript excerpts, investor deck, metrics, links, or personal notes.}}
Current belief: {{current_belief||Why this might be interesting, attractive, risky, cheap, expensive, misunderstood, or not worth time.}}
Time horizon: {{time_horizon|multi-year|Trading window, 6-12 months, multi-year, or unknown.}}
Risk constraints: {{risk_constraints||What risks, sectors, concentration, leverage, or uncertainty you want to avoid.}}

## Output

1. **Thesis in one paragraph:** the plain-English case, with confidence level.
2. **Bull/base/bear table:** what has to be true, evidence needed, catalysts, and failure signals.
3. **Business quality checklist:** moat, revenue quality, margins, capital intensity, management, balance sheet, cyclicality, and customer concentration.
4. **Valuation question:** what metric matters most and what assumption drives the conclusion.
5. **Disconfirming evidence:** the facts that would make the thesis wrong.
6. **Research plan:** the next filings, calls, competitor checks, and numbers to collect before acting.
7. **Decision boundary:** what would move this from watchlist to deeper research, or from deeper research to reject.

## Rules

[Preview stops here. Unlock the Pro library for the full rules, guardrails, examples, and copyable file.]
The rest is in the Pro library.

This preview is cut from a real Pro workflow. Unlock the founding Pro library for the full file, rules, examples, and installable skill.

Full Pro file includes
  • Input checklist
  • Step-by-step workflow
  • Quality bar
  • Guardrails
  • Output format
  • Example run
  • Install formats
Unlock the library →