Valuation Consistency Checks

Checks a finished valuation for internal consistency across its artifacts — currency agreement between cash flows and discount rate, terminal growth against the riskfree ceiling, reinvestment that pays for the growth assumed, perpetual excess returns, capital weights and beta range, equity bridge arithmetic, tax rates, and the hard constraints a company's type imposes. Grades each finding ERROR, WARN or INFO and exits 1 on any error, so it can gate a pipeline. Use before accepting a DCF, when reviewing someone else's model, when a value looks too high, or when checking terminal value assumptio

200 stars 25 forksMarketing, Sales & Business 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 valuation-consistency-checks
Manual install
git clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/valuation-consistency-checks ~/.claude/skills/valuation-consistency-checks

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

From the SKILL.md

# Valuation consistency checks

Most bad valuations contain no wrong number. They are internally inconsistent. Cash flows
sit in one currency and the discount rate was built in another. Growth appears that nobody
paid for. Terminal growth runs above the economy's. A method the company's own type rules
out was used anyway.

Each of those looks defensible when you stare at it alone. Only a check that reads several
artifacts at once catches them. That is what this script does.

Treat it as a loop, not a report:

```
run it  ->  fix what it flags  ->  run it again  ->  no errors left
```

You are done when the run comes back with zero errors and every warning has a written
defence. A warning you cannot defend is an error you have not admitted yet.

## The script

`resources/validate.py` — pure standard library, no installation needed. It reads JSON
files by path and prints findings.

```bash
python3 resources/validate.py --capital capital.json --dcf dcf.json --classification cls.json
python3 resources/validate.py --dcf dcf.json --capital capital.json --quiet
python3 resources/validate.py --dcf dcf.json --capital capital.json --json
```

| Flag | Effect |
|---|---|
| `--mandate` `--classification` `--capital` `--forecast` `--dcf` `--relative` | artifact paths |
| `--quiet` | drop the INFO and SKIP lines, show only what needs work |
| `--json` | machine-readable findings, plus `error_count` and `passed` |
Read the full skill on GitHub

Details

Skill name
valuation-consistency-checks
Path
skills/valuation-consistency-checks/SKILL.md
Repo updated
1 September 2026

FAQ

What does the Valuation Consistency Checks skill do?

Checks a finished valuation for internal consistency across its artifacts — currency agreement between cash flows and discount rate, terminal growth against the riskfree ceiling, reinvestment that pays for the growth assumed, perpetual excess returns, capital weights and beta range, equity bridge arithmetic, tax rates, and the hard constraints a company's type imposes. Grades each finding ERROR, WARN or INFO and exits 1 on any error, so it can gate a pipeline. Use before accepting a DCF, when reviewing someone else's model, when a value looks too high, or when checking terminal value assumptio

How do I install the Valuation Consistency Checks 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 Valuation Consistency Checks 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

Wc Building Block Crossover

200

lyndonkl/claude

The recombination operator for the FIFA World Cup Fantasy evolution engine. Crosses elite candidate squads/plans at BUILDING-BLOCK boundaries (Captain Core, Clean-Sheet Spine, Mid-Engine, Differential Pod, Enabler Bench; or for matchday plans the XI/captain-ladder/bench/sub/chip blocks) — harvesting the strongest module from each parent rather than swapping individual players — then runs a feasibility REPAIR operator (budget, nation cap, formation, 15-man shape) that restores legality from the cheapest block first and never guts a value-bearing block. Records block lineage (which parent each b

Marketing, Sales & Business25

Quarterly Zoomout

200

lyndonkl/claude

Synthesizes 13 weeks of substacker Growth Analyst reports + the most recent Curator review + a meta-scan of the published corpus into a 400-700 word narrative that names the quarter's shape — what happened, what changed, what held steady, what surprised. Used by the Growth Strategist at the opening of every review. Trigger keywords — quarterly, zoomout, quarter narrative, rollup, what happened this quarter.

Marketing, Sales & Business25

SEO Audit

54

southwellmedia/seo-audit

Run a full SEO audit and competitive analysis of a client website and produce a client-ready PDF proposal. Use when the user asks for an "SEO audit", to "audit this site", for "competitive analysis for [client]", "SEO for [URL]", "how is [client] doing on SEO", "what's wrong with this site from an SEO standpoint", or a pre-launch SEO check, or wants a client's search visibility, keyword strategy, local presence or AI search visibility analyzed. Covers live site recon, brand colors, competitors, keywords, technical and AI-visibility audit, content strategy, quick wins and the PDF.

Marketing, Sales & Business11

Browse the most popular Claude skills, all marketing, sales & business skills, or write your own with the skills generator.