Agent skill

Quantitative Valuation

by JoelLewis in JoelLewis/finance_skills

Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income.

MITAuto-check passedBusiness, Finance & HR

Install Quantitative Valuation

skills CLI
$ npx skills add JoelLewis/finance_skills --skill quantitative-valuation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JoelLewis/finance_skills quantitative-valuation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JoelLewis/finance_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/wealth-management/skills/quantitative-valuation .claude/skills/quantitative-valuation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
quantitative-valuation
GitHub stars
205
Token cost
~2.1k tokens
SKILL.md length
1,040 words
Files
2 (incl. scripts)
Skills in repo
91
Repo updated
First seen
Licence
MIT

At a glance

Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income.

  • The user asks about discounted cash flow
  • SKILL.md covers Core Concepts, Key Formulas, Worked Examples and Common Pitfalls, plus 2 more sections
  • Runs Python scripts from its folder; calls uv, python3 and pip
  • Dividend discount models

What it does

Quantitative Valuation is an agent skill from JoelLewis/finance_skills. Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income. Use when the user asks about discounted cash flow, DCF models, WACC, terminal value, dividend discount models, comparable multiples, or sum-of-the-parts valuation. Also trigger when users mention 'what is this stock worth', 'fair value estimate', 'Gordon growth model', 'free cash flow valuation', 'cost of equity', 'sensitivity analysis', 'exit multiple', or ask whether a stock is…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/quantitative_valuation.py`).

It sits in Business, Finance & HR, covering Financial modeling. The repository describes itself as: Claude Code skill plugins for financial services — 81 skills across 7 domain plugins covering investment management, compliance, advisory practice, trading, and operations. The licence is MIT.

When your agent uses it

  • The user asks about discounted cash flow
  • Dividend discount models
  • Comparable multiples
  • Sum-of-the-parts valuation

Example prompts

  • “what is this stock worth”
  • “fair value estimate”
  • “Gordon growth model”
  • “/quantitative-valuation”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 5c498ea. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv
    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv and pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quantitative Valuation loads about 2.1k tokens when it runs. Until then it costs about 140 tokens; SKILL.md has 1,040 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from JoelLewis/finance_skills at commit 5c498ea, republished under its MIT licence (© JoelLewis). 1,040 words, ~2,072 tokens.

Download SKILL.mdSave it as .claude/skills/quantitative-valuation/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
quantitative-valuation
description
Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income. Use when the user asks about discounted cash flow, DCF models, WACC, terminal value, dividend discount models, comparable multiples, or sum-of-the-parts valuation. Also trigger when users mention 'what is this stock worth', 'fair value estimate', 'Gordon growth model', 'free cash flow valuation', 'cost of equity', 'sensitivity analysis', 'exit multiple', or ask whether a stock is overvalued or undervalued.

Quantitative Valuation

Core Concepts

Discounted Cash Flow (DCF)

The DCF model values a company as the present value of its future free cash flows plus a terminal value:

V = Σ FCF_t / (1 + WACC)^t + TV / (1 + WACC)^n

where FCF_t is the free cash flow in year t, WACC is the weighted average cost of capital, and TV is the terminal value at the end of the explicit forecast period.

Terminal Value — Gordon Growth Model

Estimates the value of all cash flows beyond the explicit forecast period assuming perpetual growth:

TV = FCF_n × (1 + g) / (WACC - g)

where g is the long-term sustainable growth rate (typically near nominal GDP growth, 2-4%).

Terminal Value — Exit Multiple Method

Estimates terminal value by applying a market multiple to the final-year financial metric:

TV = EBITDA_n × EV/EBITDA multiple

The exit multiple is typically based on current peer trading multiples or long-run sector averages.

Weighted Average Cost of Capital (WACC)

Blends the cost of equity and after-tax cost of debt weighted by their market-value proportions:

WACC = w_e × r_e + w_d × r_d × (1 - τ)

where w_e and w_d are equity and debt weights, r_e and r_d are their respective costs, and τ is the marginal tax rate.

Cost of Equity — CAPM

The Capital Asset Pricing Model estimates the required return on equity:

r_e = R_f + β × (R_m - R_f)

where R_f is the risk-free rate, β is the stock's sensitivity to market returns, and (R_m - R_f) is the equity risk premium.

Dividend Discount Model (DDM)

Values a stock as the present value of its future dividends. The Gordon Growth (single-stage) form:

P = D_1 / (r - g)

where D_1 is the next-period dividend, r is the required return, and g is the constant dividend growth rate.

Multi-Stage DDM

Accommodates companies transitioning through growth phases:

  • Stage 1 (High growth): Dividends grow at g_1 for n years
  • Stage 2 (Transition): Growth declines linearly from g_1 to g_3
  • Stage 3 (Stable): Dividends grow at g_3 in perpetuity (valued via Gordon Growth)
Residual Income Model

Values a company as its book value plus the present value of economic profits:

V = BV_0 + Σ (ROE - r) × BV_{t-1} / (1 + r)^t

This model is useful when free cash flows are negative but the company earns above its cost of equity.

Comparable Multiples

Relative valuation uses pricing ratios from a peer group to infer value:

  • P/E (Price-to-Earnings): most common for profitable companies
  • EV/EBITDA (Enterprise Value to EBITDA): capital-structure neutral
  • P/S (Price-to-Sales): useful for unprofitable or early-stage companies
  • P/B (Price-to-Book): useful for asset-heavy businesses (banks, REITs)

Use the median of the peer group to reduce outlier effects. Adjust for differences in growth, margins, and risk.

Relative Valuation

Compare a stock's current multiple to:

  • Its own historical average (time-series comparison)
  • Sector or industry median (cross-sectional comparison)

A stock trading at a discount to both may be undervalued, or there may be fundamental deterioration.

Sum-of-the-Parts (SOTP)

Value each business segment separately using the most appropriate method (DCF, multiples, or asset-based), then sum. Subtract net debt and add non-operating assets to arrive at equity value.

Sensitivity Analysis

Vary key assumptions (WACC and terminal growth rate are the most impactful) in a two-way data table to understand the range of possible valuations. This exposes which assumptions drive the result.

Key Formulas

FormulaExpressionUse Case
DCF ValueV = Σ FCF_t/(1+WACC)^t + TV/(1+WACC)^nEnterprise valuation from cash flows
Gordon Growth TVTV = FCF_n×(1+g)/(WACC-g)Terminal value assuming perpetual growth
Exit Multiple TVTV = EBITDA_n × multipleTerminal value using market multiples
WACCWACC = w_e×r_e + w_d×r_d×(1-τ)Blended discount rate
CAPMr_e = R_f + β×(R_m - R_f)Cost of equity estimation
Gordon Growth DDMP = D_1/(r-g)Stock value from dividends
Residual IncomeV = BV_0 + Σ (ROE-r)×BV_{t-1}/(1+r)^tValue from economic profit
Implied Value (Comps)V = Metric × Peer Median MultipleRelative valuation

Worked Examples

Show full SKILL.md (425 more words)Show less
Example 1: Two-Stage DCF

Given:

  • Current FCF: $100M
  • Stage 1: 15% FCF growth for 5 years
  • Terminal growth rate: 3%
  • WACC: 10%

Calculate: Enterprise value

Solution:

Projected free cash flows:

  • Year 1: $100M × 1.15 = $115.0M
  • Year 2: $115M × 1.15 = $132.3M
  • Year 3: $132.3M × 1.15 = $152.1M
  • Year 4: $152.1M × 1.15 = $174.9M
  • Year 5: $174.9M × 1.15 = $201.1M

PV of Stage 1 cash flows:

  • PV = $115.0/1.10 + $132.3/1.10² + $152.1/1.10³ + $174.9/1.10⁴ + $201.1/1.10⁵
  • PV = $104.5 + $109.3 + $114.3 + $119.5 + $124.9 = $572.5M

Terminal value (Gordon Growth):

  • TV = $201.1M × 1.03 / (0.10 - 0.03) = $207.2M / 0.07 = $2,959.6M
  • PV of TV = $2,959.6M / 1.10⁵ = $1,837.7M

Enterprise Value = $572.5M + $1,837.7M = $2,410.1M

Note: Terminal value represents 76% of total value, which is typical but underscores the importance of terminal assumptions.

Example 2: Comparable P/E Analysis

Given:

  • Target company EPS: $5.00
  • Peer group P/E ratios: 15x, 17x, 18x, 19x, 22x

Calculate: Implied share price using peer median

Solution:

Peer median P/E = 18x (middle value of the sorted set)

Implied share price = EPS × Peer Median P/E = $5.00 × 18 = $90.00

If the stock trades at $75, it appears undervalued relative to peers (16.7% discount). Before concluding, check whether lower growth, margins, or higher risk justify the discount.

Common Pitfalls

  • Terminal value dominates DCF output (often 60-80% of total value) — scrutinize terminal assumptions carefully
  • Garbage-in-garbage-out: a DCF is only as good as its assumptions; false precision gives false confidence
  • Using trailing multiples when forward multiples are more relevant for fast-growing or cyclical companies
  • Not adjusting comparable multiples for differences in growth rates, margins, and capital structure
  • Circular reference when WACC depends on market cap which depends on the WACC-derived valuation — iterate or use target capital structure
  • Projecting high growth rates indefinitely without considering competitive dynamics and mean reversion
  • Ignoring dilution from stock-based compensation in per-share value estimates

Cross-References

  • historical-risk (wealth-management plugin): historical beta estimation for CAPM inputs
  • forward-risk (wealth-management plugin): cost of equity estimation via CAPM and factor models
  • financial-statements (wealth-management plugin): FCF and EBITDA derivation from financials
  • qualitative-valuation (wealth-management plugin): complements quantitative models with moat and quality analysis
  • asset-allocation (wealth-management plugin): valuation outputs feed into portfolio construction decisions

Running the script

uv run scripts/quantitative_valuation.py

The PEP 723 header resolves the numpy dependency automatically. Alternatively run python3 scripts/quantitative_valuation.py after pip install numpy.

  • Bare run prints a demo covering WACC/CAPM, a two-stage DCF with sensitivity table, dividend discount models, residual income, and comparable multiples.
  • --verify re-runs the demo computations and asserts the outputs match this skill's worked examples (prints PASS/FAIL, nonzero exit on mismatch).
  • --help lists the available classes.

The file is primarily meant to be imported as a module, e.g. from quantitative_valuation import DCF, WACC, DividendDiscount, ComparableMultiples.

© JoelLewis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in plugins/wealth-management/skills/quantitative-valuation of JoelLewis/finance_skills.

  • SKILL.md
  • scripts/quantitative_valuation.py

Open the folder on GitHubat commit 5c498ea

Compare with similar skills

Quantitative Valuation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Quantitative Valuation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Quantitative Valuation this skillJoelLewis/finance_skills205—~2.1kAutomated safety check: PassMIT
Creating Financial ModelsChen-zexi/open-ptc-agent7293 repos~1.3kAutomated safety check: PassMIT
Equity ResearchrollingSirius/equity-research-skill453—~1.5kAutomated safety check: PassMIT
SaaS Metrics Coachrongxinzy/RongxinAI1542 repos~1.3kAutomated safety check: PassMIT
Startup Financial Modelingnicepkg/auto-company19411 repos~2.8kAutomated safety check: PassNone
Stock Value AnalyzerFunnyKun/stock-value-analyzer140—~3.3kAutomated safety check: PassNone

Similar skills

  • Creating Financial Models

    Chen-zexi/open-ptc-agent

    This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

    729 GitHub starsUsed in 3 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Equity Research

    rollingSirius/equity-research-skill

    撰写机构级个股投资研究报告(二级市场深度研究)。Use whenever the user wants to research, analyze, or value a specific publicly-traded stock — e.g.

    453 GitHub stars~1.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • SaaS Metrics Coach

    rongxinzy/RongxinAI

    SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.

    154 GitHub starsUsed in 2 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Startup Financial Modeling

    nicepkg/auto-company

    This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or…

    194 GitHub starsUsed in 11 repos~2.8k tokens
    Business, Finance & HRAuto-check passed
  • Stock Value Analyzer

    FunnyKun/stock-value-analyzer

    基于邱国鹭《投资中最简单的事》方法论的股票价值分析器(v2.0 双层架构)。通过"三好原则"(好行业、好公司、好价格)系统评估一只股票是否值得投资。v2.0 在原定性框架之上注入一套可量化、可复现的硬模型层——反向 DCF 反解市场隐含增速、情景概率加权估值、EPV 盈利能力价值、分行业估值路由、杜邦三/五因子分解、ROIC vs WACC、Piotroski F-Score、Beneish…

    140 GitHub stars~3.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Dcf Valuation

    edinetdb/dexter-jp

    Performs discounted cash flow (DCF) valuation analysis to estimate intrinsic value per share for Japanese listed companies.

    311 GitHub stars~1.1k tokensUpdated today
    Business, Finance & HRAuto-check passed

More from JoelLewis/finance_skills

All 91 skills in this repo
  • Asset Allocation

    JoelLewis/finance_skills

    Determine how to distribute capital across asset classes using strategic and tactical allocation frameworks.

    205 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Bet Sizing

    JoelLewis/finance_skills

    Determine how much capital to allocate to individual positions within a portfolio.

    205 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Commodities

    JoelLewis/finance_skills

    Analyze commodity markets including futures curve dynamics, roll yield, and supply/demand fundamentals.

    205 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Currencies And Fx

    JoelLewis/finance_skills

    Analyze currency markets, exchange rate mechanics, and FX risk management for international portfolios.

    205 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Debt Management

    JoelLewis/finance_skills

    Provide frameworks for managing and paying off personal debt effectively.

    205 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Diversification

    JoelLewis/finance_skills

    Build diversified portfolios using correlation analysis, efficient frontier construction, and factor-based diversification.

    205 GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Quantitative Valuation

What does Quantitative Valuation do?

Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income. Quantitative Valuation is an agent skill from JoelLewis/finance_skills. Estimate intrinsic value of stocks and companies using DCF, dividend discount models, comparable multiples, and residual income.

When should I use Quantitative Valuation?

Quantitative Valuation fits situations like: the user asks about discounted cash flow; dividend discount models; comparable multiples; sum-of-the-parts valuation.

How do I install Quantitative Valuation in Claude Code?

Run `npx skills add JoelLewis/finance_skills --skill quantitative-valuation -a claude-code`. Or copy the skill folder (plugins/wealth-management/skills/quantitative-valuation in JoelLewis/finance_skills) into .claude/skills/quantitative-valuation in your project. Claude Code loads it when a task matches its description.

How do I install Quantitative Valuation in Codex?

Run `npx skills add JoelLewis/finance_skills --skill quantitative-valuation -a codex`. Or copy the skill folder (plugins/wealth-management/skills/quantitative-valuation in JoelLewis/finance_skills) into .agents/skills/quantitative-valuation in your project. Codex loads it when a task matches its description.

Can I use Quantitative Valuation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JoelLewis/finance_skills --skill quantitative-valuation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quantitative-valuation, .gemini/skills/quantitative-valuation, .github/skills/quantitative-valuation and .opencode/skills/quantitative-valuation in your project.

What does Quantitative Valuation need to run?

Going by SKILL.md and its folder, Quantitative Valuation needs Python for the scripts in its folder and the command-line tools its instructions call (uv, python3 and pip). Our summary lists: Python 3.

Does Quantitative Valuation access the network?

SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Quantitative Valuation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Quantitative Valuation use?

Quantitative Valuation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Quantitative Valuation use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Quantitative Valuation?

Skills that share tags, products or a category with Quantitative Valuation: Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars), Equity Research (rollingSirius/equity-research-skill, 453 stars), SaaS Metrics Coach (rongxinzy/RongxinAI, 154 stars) and Startup Financial Modeling (nicepkg/auto-company, 194 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Quantitative Valuation?

JoelLewis (a GitHub user) maintains it in JoelLewis/finance_skills, which has 205 GitHub stars. The repository holds 91 skills in this directory. The repository was last updated on July 18, 2026.

Source: JoelLewis/finance_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.