Thesis tracker
Skill w95/awesome-claude-corporate-skills/02-finance-accounting/thesis-tracker
166 production-ready Claude AI skills organized by corporate role — executive leadership, finance, HR, marketing, sales, legal, operations, engineering, product, data, customer success, procurement & document processingFrom the repository description
npx -y skills add w95/awesome-claude-corporate-skills --skill thesis-trackerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.6 KB, 610 tokens by cl100k_base, as published. Nobody here has run it
Thesis Tracker
description: Maintain and update investment theses for portfolio positions and watchlist names. Track key data points, catalysts, and thesis milestones over time. Use when updating a thesis with new information, reviewing position rationale, or checking if a thesis is still intact. Triggers on "update thesis for [company]", "is my thesis still intact", "thesis check", "add data point to [company]", or "review my positions".
Workflow
Step 1: Define or Load Thesis
If creating a new thesis:
- Company: Name and ticker
- Position: Long or Short
- Thesis statement: 1-2 sentence core thesis (e.g., "Long ACME — margin expansion from pricing power + operating leverage as mix shifts to software")
- Key pillars: 3-5 supporting arguments
- Key risks: 3-5 risks that would invalidate the thesis
- Catalysts: Upcoming events that could prove/disprove the thesis (earnings, product launches, regulatory decisions)
- Target price / valuation: What's it worth if the thesis plays out
- Stop-loss trigger: What would make you exit
If updating an existing thesis, ask the user for the new data point or development.
Step 2: Update Log
For each new data point or development:
- Date: When this happened
- Data point: What changed (earnings beat, management departure, competitor move, etc.)
- Thesis impact: Does this strengthen, weaken, or neutralize a specific pillar?
- Action: No change / Increase position / Trim / Exit
- Updated conviction: High / Medium / Low
Step 3: Thesis Scorecard
Maintain a running scorecard:
| Pillar | Original Expectation | Current Status | Trend |
|---|---|---|---|
| Revenue growth >20% | On track | Q3 was 22% | Stable |
| Margin expansion | Behind | Margins flat YoY | Concerning |
| New product launch | Pending | Delayed to Q2 | Watch |
Step 4: Catalyst Calendar
Track upcoming catalysts:
| Date | Event | Expected Impact | Notes |
|---|---|---|---|
Step 5: Output
Thesis summary suitable for:
- Morning meeting discussion
- Portfolio review
- Risk committee presentation
Format: Concise markdown or Word doc with the scorecard, recent updates, and current conviction level.
Important Notes
- A thesis should be falsifiable — if nothing could disprove it, it's not a thesis
- Track disconfirming evidence as rigorously as confirming evidence
- Review theses at least quarterly, even when nothing dramatic has happened
- If the user manages multiple positions, offer to do a full portfolio thesis review
- Store thesis data in a structured format so it can be referenced across sessions
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most literature review skills give in 610 tokens
Counted across 185 of the 191 authors here whose files we hold, read 2026-09-06
- Screen sources by title, abstract, then full textin 16 of 185, across 9 files
- Create a search protocol before collecting sourcesin 11 of 185, across 5 files
- Convert the prompt into a searchable research questionin 11 of 185, across 5 files
- Keep a reproducible search login 11 of 185, across 5 files
- Group evidence by theme, not per paperin 11 of 185, across 5 files
- Ask the user which review rigor level is neededin 11 of 185, across 5 files
- Use a structured extraction tablein 11 of 185, across 5 files
- Separate claims by confidence levelin 10 of 185, across 4 files
- Deduplicate by DOI, identifier, then titlein 10 of 185, across 4 files
- Record exclusion reasons at each screening stagein 9 of 185, across 3 files
- Verify citation identifiers before finalizingin 9 of 185, across 4 files
- Search a minimum of three databasesin 7 of 185, across 6 files
Said here and by no other author read
- Define new theses with statement, pillars, risks, and catalysts
- Produce a concise summary with scorecard, updates, and conviction
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.