Jason Zou
Jason Zou · Economics and Philosophy, University of ChicagoUpdated 30 September 2026

Finance tools by Jason Zou

This site documents six tools I built for equity research and portfolio work. They run as Claude skills and plugins. Each one has its own page explaining how it works, what checks it runs on itself and which decisions it doesn't make for you. The site also runs a cost-aware classifier, a web app that measures which Claude model is worth paying for when labelling news headlines.

  1. 01Stock diligence pack · builds a linked three-statement DCF on a listed company and writes the report around it
  2. 02Reverse DCF · works out the growth and margins a share price already assumes
  3. 03Direct indexing basket · tracks an index with a smaller basket of its stocks
  4. 04Stock screener · puts any ticker on the same fixed dashboard
  5. 05Cost-aware classifier · finds the cheapest Claude model good enough to label news headlines for a sentiment signal
  6. 06Two smaller tools · a correlated substitutes finder and a MACD signal test
See the tools

All six are my own work. Spotify is the worked example used across the site, starting with the chart on the right.

Example output · the diligence pack on SpotifyValue per share by case
$800$600$400$200$0 Price $543.17 · 4 Sep 2026 $290$515$602$721 BearStreetManagementBull
Source
SPOT_DCF.xlsx, rebuilt from the plugin's input file and recalculated for all four cases; 14 tabs, 1,984 formulas
Checks
17, all passed in the Street case (the case built on consensus forecasts)
Output
Test-run output, not a valuation of Spotify. The Street case comes out 5.2% below the share price. The management case, built from management's own targets, comes out 10.8% above it
01ToolsFour main tools, two smaller ones and a web app

The tools

Each card opens a page on one of the seven tools, three of which have public repositories. Skills are folders of instructions and scripts that Claude runs. A plugin bundles several skills, and a subagent is a separate model pass with its own brief.

01
Claude plugin12 skills · 10 subagents · 15 scripts

Stock diligence pack

Builds a linked three-statement DCF, with a debt schedule and the bridge from enterprise value to equity, then writes the report and a memo on each forecast lever. Spotify is the worked example on this site.

Workbook14 tabs · 17 checksReport13 sections + 7 appendicesExampleSpotify, Sept 2026
Bear, Street, management and bull casesOpen the page
02
Inside the packClosed-form solution

Reverse DCF

Starts from the share price and works out the perpetual growth and exit multiple it implies. Then it shows which growth and margin pairs clear that price.

Spotify3.6% implied growthExit12.5x EV/EBIT impliedTry itfictional XMPL grid
Which growth and margin pairs justify the priceTry the grid
03
Claude skillFive-sheet workbook and backtest

Direct indexing basket

Builds a smaller basket of stocks that tracks an equity index, by default 75 names for the S&P 500. It backtests the basket and reports its tracking error (how far its returns stray from the index's) at each basket size.

Methodstratified by sector, then filled to cut tracking errorWeightscapped, sum to 1.0000Repopublic
Tracking error by basket sizeOpen the page
04
Claude skillFixed template, data only

Stock screener

Pulls prices, five years of fundamentals, drawdowns, what analysts expect (the Street) and news for one ticker, and lays them out on a fixed six-tab dashboard. The full dashboard runs on its page with synthetic data.

Tabs6 for a stock, 5 for an ETFChecksa checklist runs before it rendersRepopublic
XMPL, weekly, five yearsOpen the dashboard
05 and 06 · Smaller tools
07 · Web app
02Example runSPOT_DCF.xlsx · valuation date 4 September 2026

An example run of the diligence pack

Spotify is the worked example throughout this site. The workbook shown here is rebuilt from the plugin's own input file and recalculated. Each figure below links to where it sits on the diligence page.

Model output · the workbook's third sensitivity gridStatus · ALL OK
Implied value per share · revenue CAGR FY2025–35 × FY2035 EBIT margin · Street case
$547.22at 10% growth and a 28% terminal margin, the cell nearest the $543.17 price
CAGR ↓ · margin →16%20%24%28%32%
8%315368422475529
10%357421484547610
12%407482556631706
14%465553640728816
16%531635738841945
SourceSPOT_DCF.xlsx · Sensitivity!B33:F37, US dollars per share, rounded Enginethis grid uses a simplified reverse-DCF engine. The workbook's other two sensitivity grids use the full three-statement cash flows ReadingCells in turquoise are worth more than today's price (the workbook itself shades them green and red). Holding a 24% terminal margin, the price needs roughly a 12% ten-year revenue CAGR. At a 20% margin it needs about 14%.

The reverse DCF

Before asking what the stock is worth, the model works out what would have to be true for today's price to be right. It sets the answer out as a grid of growth and margin pairs.

  1. 01Start with the market enterprise value, taken from the share price and the equity bridge.
  2. 02Work out the terminal value that enterprise value requires, given the explicit cash flows.
  3. 03Solve in closed form for the perpetual growth rate and exit multiple that terminal value implies.
  4. 04Find the growth and margin pairs that clear the price.
03MethodFive stages

How the tools work

All six tools follow some part of the same five stages, and the diligence pack runs all five. The screener and MACD test stop at Check, and the basket builder and substitutes finder stop at Build. Scroll through the stages and the panel follows.

  1. 01

    Source

    The coordinating agent saves the filings, decks and transcripts, and a script, data_pull.py, pulls prices, statements, estimates, earnings dates, insider transactions, holders and FX. Gaps are recorded in the manifest (the file that lists every source and every gap) rather than filled in.

  2. 02

    Build

    Every numeric exhibit is computed. The workbook is built from one input file, so a figure copied from a filing lives in one place and every formula reads from it.

  3. 03

    Check

    The model is recalculated and run through its checks across four cases and three switches, such as the choice of terminal method. It is not delivered until it recalculates with zero formula errors and passes every check in the Street case.

  4. 04

    Review

    Five reviewers, each prompted as a different reader, return ranked findings tagged FAIL or IMPROVE. They do not edit anything themselves; the fixes are made afterwards and the file re-rendered.

  5. 05

    Decide

    The view on the company, the scenario weights, any price target and the sign-off on adapted assumptions are yours. The tools do not make recommendations.

Stage 01Sources, ranked by how much they can be trusted
InputSourceRule
Statements, five yearsFilings first, then the data provider's standardised statementsReconcile when they differ by more than 2%
Prices, ten yearsYahoo FinanceFixed reference dates for every return
Estimates and targetsConsensus as reportedBlank rather than guessed when a broker did not disclose
Management targetsInvestor Day, transcriptsRecorded with the date they were given
GapsMANIFEST.mdListed with what was tried
dcf_config_TICKER.json → dcf_build.py → TICKER_DCF.xlsx
inputs market data, discount rate, switches, equity bridge
drivers 14 forecast levers × 4 scenarios, one Selected row each
schedules revenue build · margins · working capital · capex
debt by instrument · tax · equity roll-forward
outputs unlevered FCF · both terminal methods · EV to equity bridge
grids three live sensitivities, each cell its own DCF
// 1,984 live formulas for Spotify
CheckRuleStreet
Balance sheet balances every year< 0.5OK
Cash never negative≥ 0OK
WACC exceeds terminal growth> 2 ptsOK
Terminal value share of EV40–85%OK
CF closing cash equals BS cash0OK
Debt schedule ties to balance sheet0OK
Sensitivity grid centre equals DCF price0OK
Overall status · 17 checksALL OK
  1. R1Investment partner · reads the model for what the price already implies, the probability-weighted value, the return skew and a pre-mortem
  2. R2Banking managing director · reviews the capital structure, debt capacity, change-of-control constraints and strategic options
  3. R3Research partner · goes through the model against consensus line by line, then the guidance ledger and the setup for the next print
  4. R4Red team · hunts for claims with no mechanism behind them, figures quoted from memory and benchmarks that contradict the narrative
  5. R5QA · checks the numbers in the prose against the tables, and looks for leftover placeholders and breaches of the style rules

The tool

  • Data pulls, exhibits and charts
  • Building, recalculating and checking the model
  • Drafting sections and rendering the report
  • A five-reader review with ranked findings

You

  • The view on the company
  • Scenario weights and any price target
  • Sign-off on adapted assumptions
  • Which open items matter
04AboutJason Zou · Chicago

About

I study Economics and Philosophy at the University of Chicago. The tools I've built so far help you get up to speed on a company, read what a share price assumes, track an index with fewer names and give any ticker the same first look.

All of them run as Claude skills or plugins that I designed and built. Spotify is the worked example for the diligence pack, and the screener has been run on eight tickers.

Email
jzou1@uchicago.edu
GitHub
github.com/JasonZou64920
LinkedIn
linkedin.com/in/rxjasonzou
Study
Economics and Philosophy, University of Chicago
Builds with
Python, Excel and LibreOffice for the models, Claude skills and plugins for the runs, and Cloudflare Workers for this site
Ask
05Notes

Notes

These notes say which numbers on this site come from a real run, which are illustrative, and what the technical terms mean.

Spotify figures
The workbook is rebuilt from the plugin's input file and recalculated in LibreOffice for all four cases. The €154m exchangeable notes gain is corrected to net of FX, per its label. Consensus is Yahoo Finance's as of 4 September 2026.
Illustrative examples
The XMPL ticker in the screener and the reverse DCF grid is made up, as are the placeholder names and weights in the basket workbook. They show how each tool works. None comes from a run, and all are labelled.
Terms
The Street means the sell-side analysts who publish estimates, and consensus is their average. A skill is a folder of instructions and scripts that Claude runs on request, a plugin bundles several skills, and a subagent is a separate model pass with its own brief.

Repositories and contact

Three of the seven tools have public repositories. The diligence plugin, which includes the reverse DCF, and the MACD test aren't published yet. You can still read the Spotify workbook, the plugin source and the XMPL dashboard on the pages above without downloading anything.

Emailjzou1@uchicago.edu GitHubgithub.com/JasonZou64920 LinkedInlinkedin.com/in/rxjasonzou Siteprojects.jasonzou.com · version 4.1 Updated30 September 2026