Financial Statement Normalization

Converts reported financial statements into valuation-ready numbers — capitalizes R&D into a research asset, capitalizes operating leases into debt, strips one-time items, normalizes cyclical or trough earnings, derives FCFF and FCFE, and computes invested capital, ROIC, economic value added and the diagnostic ratio pack. Use when cleaning up EBIT before a DCF, capitalizing research or leases, deciding whether a restructuring charge is really non-recurring, computing free cash flow to the firm or to equity, measuring return on invested capital, normalizing earnings for a cyclical or commodity

200 stars 25 forksFinance & Crypto Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add lyndonkl/claude

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add lyndonkl/claude --skill financial-statement-normalization
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/financial-statement-normalization ~/.claude/skills/financial-statement-normalization

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Financial statement normalization

Accounting statements are not built for valuation. They are built to be auditable and
comparable, and those goals push them away from economic substance in three specific ways.
Research spending is an investment that the accountant expensed. Leases are debt that sat
off the balance sheet for decades and still get reported on rules nobody trusts. One-time
items sit inside operating income and get relabelled by management every year.

This skill applies the corrections and then derives what follows from them: cash flows,
the capital base, and the return earned on that capital. Every number the script produces
is a pure transform of numbers you supply. Which items are non-recurring, and how long
research takes to pay off in this business, are your calls.

## The script

`resources/normalize.py` — pure standard library, no installation needed. Every subcommand
takes JSON on stdin (or `--in FILE`) and prints JSON.

```bash
python3 resources/normalize.py <subcommand> --example    # show the input shape
python3 resources/normalize.py <subcommand> --in payload.json
python3 resources/normalize.py selftest                  # verify the engine
```

| Subcommand | Turns this | Into this |
|---|---|---|
| `capitalize-rd` | R&D history and an amortizable life | research asset, this year's amortization, the EBIT adjustment |
Read the full skill on GitHub

Details

Skill name
financial-statement-normalization
Path
skills/financial-statement-normalization/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Financial Statement Normalization skill do?

Converts reported financial statements into valuation-ready numbers — capitalizes R&D into a research asset, capitalizes operating leases into debt, strips one-time items, normalizes cyclical or trough earnings, derives FCFF and FCFE, and computes invested capital, ROIC, economic value added and the diagnostic ratio pack. Use when cleaning up EBIT before a DCF, capitalizing research or leases, deciding whether a restructuring charge is really non-recurring, computing free cash flow to the firm or to equity, measuring return on invested capital, normalizing earnings for a cyclical or commodity

How do I install the Financial Statement Normalization skill?

Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Financial Statement Normalization popular?

It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.

Related skills

Abstraction Concrete Examples

200

lyndonkl/claude

Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.

Testing & QA25

Academic Letter Architect

200

lyndonkl/claude

Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.

Research & Science25

Adr Architecture

200

lyndonkl/claude

Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.

Software Development25

Financial Unit Economics

200

lyndonkl/claude

Analyzes profitability per customer, product, or transaction to determine business model viability and scalability. Covers CAC, LTV, contribution margin, cohort analysis, and growth-readiness assessment. Use when evaluating business model viability, validating startup metrics (CAC, LTV, payback period), making pricing decisions, comparing business models, or when user mentions unit economics, CAC/LTV ratio, contribution margin, customer profitability, or break-even analysis.

Finance & Crypto25

Financial Data Sourcing

200

lyndonkl/claude

Maps every input a company analysis needs to where it comes from — filing line items, market data, Damodaran reference datasets, macro series — with units, update frequency, acceptable fallbacks and the consistency rules that bind them. Use when gathering data for a valuation, when an input is missing and a substitute is needed, when deciding whether a user-supplied figure can be accepted at face value, or when checking that figures are internally consistent.

Finance & Crypto25

Freqtrade

213

TerminalSkills/skills

Freqtrade is a free, open-source crypto trading bot written in Python: you write a strategy class, download exchange candles, backtest it, then run it in dry-run mode (simulated orders) before risking money. Use when a user says "backtest a crypto strategy", "download historical candles for freqtrade", "write a freqtrade strategy", "run a trading bot in dry-run", or "set up FreqUI". Not financial advice: strategies usually lose money, and live trading can lose all of it. This skill defaults to dry-run and never handles exchange keys.

Finance & Crypto34

Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.