Dcf Valuation logo

Dcf Valuation

Organization
claude-office-skills
dcf-valuation

Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.

Overview

Publisherclaude-office-skills
Repositoryskills
Skill namedcf-valuation
Stars
514
Forks
97
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by claude-office-skills on GitHub. Read the source before you install it.

Installation

Install the Dcf Valuation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/claude-office-skills/skills/tree/main/dcf-valuation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/claude-office-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/dcf-valuation .claude/skills/dcf-valuation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dcf Valuation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dcf Valuation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dcf Valuation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

DCF Valuation Skill

Overview

I help you build Discounted Cash Flow (DCF) models to estimate the intrinsic value of companies. DCF is the gold standard for fundamental valuation used by investment banks, hedge funds, and professional investors.

What I can do:

  • Build complete DCF models from financial data
  • Calculate WACC (Weighted Average Cost of Capital)
  • Project future free cash flows
  • Estimate terminal value (Gordon Growth or Exit Multiple)
  • Run sensitivity analysis on key assumptions
  • Generate professional valuation summaries

What I cannot do:

  • Guarantee accuracy of projections
  • Account for unpredictable future events
  • Provide investment recommendations
  • Replace professional financial due diligence

How to Use Me

Step 1: Provide Financial Data

I need:

  • Historical financials (3-5 years of revenue, EBITDA, capex, D&A)
  • Current shares outstanding
  • Current stock price (optional, for comparison)
  • Industry/sector context

Step 2: Set Assumptions

Key assumptions to specify (or I'll use industry defaults):

  • Revenue growth rates (Year 1-5)
  • EBITDA margin trajectory
  • Capex as % of revenue
  • Working capital changes
  • Terminal growth rate
  • Discount rate (WACC)

Step 3: Choose Model Type

  • Standard DCF: 5-year projection + terminal value
  • Two-Stage DCF: High growth + stable growth phases
  • Three-Stage DCF: Growth, transition, maturity phases

DCF Model Framework

Step 1: Project Free Cash Flow (FCF)

Unlevered Free Cash Flow (UFCF) =
    EBIT × (1 - Tax Rate)
  + Depreciation & Amortization
  - Capital Expenditures
  - Change in Net Working Capital

Step 2: Calculate WACC

WACC = (E/V × Re) + (D/V × Rd × (1 - Tc))

Where:
E = Market value of equity
D = Market value of debt
V = E + D (total value)
Re = Cost of equity (CAPM: Rf + β × Market Risk Premium)
Rd = Cost of debt
Tc = Corporate tax rate
CAPM Formula for Cost of Equity
Re = Rf + β × (Rm - Rf)

Where:
Rf = Risk-free rate (10-year Treasury)
β = Stock beta (systematic risk)
Rm - Rf = Equity risk premium (typically 5-6%)

Step 3: Calculate Terminal Value

Method A: Gordon Growth Model
Terminal Value = FCF(n+1) / (WACC - g)

Where:
FCF(n+1) = Final year FCF × (1 + g)
g = Terminal growth rate (typically 2-3%, ≤ GDP growth)
Method B: Exit Multiple
Terminal Value = EBITDA(n) × Exit Multiple

Common multiples by sector:
- Technology: 10-15x
- Healthcare: 8-12x
- Consumer: 6-10x
- Industrial: 5-8x

Step 4: Discount to Present Value

Enterprise Value = Σ [FCF(t) / (1 + WACC)^t] + [TV / (1 + WACC)^n]

Equity Value = Enterprise Value - Net Debt + Cash

Intrinsic Value per Share = Equity Value / Shares Outstanding

Output Format

markdown
# DCF Valuation Model: [Company Name]

**Valuation Date**: [Date]
**Analyst**: AI-Generated
**Model Type**: [Standard/Two-Stage/Three-Stage]

---

## Executive Summary

| Metric | Value |
|--------|-------|
| **Intrinsic Value per Share** | $XX.XX |
| **Current Market Price** | $XX.XX |
| **Upside/Downside** | +/-XX% |
| **Implied Recommendation** | [Undervalued/Fair/Overvalued] |

---

## Key Assumptions

### Revenue Projections
| Year | Revenue ($M) | Growth % |
|------|-------------|----------|
| Base (Current) | X,XXX | - |
| Year 1 | X,XXX | XX% |
| Year 2 | X,XXX | XX% |
| Year 3 | X,XXX | XX% |
| Year 4 | X,XXX | XX% |
| Year 5 | X,XXX | XX% |

### Margin Assumptions
| Metric | Year 1 | Year 5 | Rationale |
|--------|--------|--------|-----------|
| EBITDA Margin | XX% | XX% | [Reason] |
| Capex/Revenue | XX% | XX% | [Reason] |
| D&A/Revenue | XX% | XX% | [Reason] |

### WACC Calculation
| Component | Value | Source/Assumption |
|-----------|-------|-------------------|
| Risk-free Rate | X.X% | 10-Year Treasury |
| Beta | X.XX | Bloomberg/Calculated |
| Equity Risk Premium | X.X% | Historical average |
| Cost of Equity | XX.X% | CAPM |
| Cost of Debt | X.X% | Credit spread |
| Tax Rate | XX% | Effective rate |
| Debt/Total Capital | XX% | Current structure |
| **WACC** | **X.X%** | |

### Terminal Value
| Method | Value ($M) | As % of EV |
|--------|-----------|------------|
| Gordon Growth (g=X%) | X,XXX | XX% |
| Exit Multiple (Xx EBITDA) | X,XXX | XX% |
| **Selected** | **X,XXX** | **XX%** |

---

## Free Cash Flow Projections

| ($M) | Year 1 | Year 2 | Year 3 | Year 4 | Year 5 | Terminal |
|------|--------|--------|--------|--------|--------|----------|
| Revenue | | | | | | |
| EBITDA | | | | | | |
| (-) D&A | | | | | | |
| EBIT | | | | | | |
| (-) Taxes | | | | | | |
| NOPAT | | | | | | |
| (+) D&A | | | | | | |
| (-) Capex | | | | | | |
| (-) ΔNWC | | | | | | |
| **UFCF** | | | | | | |

---

## Valuation Summary

| Component | Value ($M) |
|-----------|-----------|
| PV of Projected FCFs | X,XXX |
| PV of Terminal Value | X,XXX |
| **Enterprise Value** | **X,XXX** |
| (-) Net Debt | (X,XXX) |
| (+) Cash | X,XXX |
| **Equity Value** | **X,XXX** |
| Shares Outstanding | XXX M |
| **Value per Share** | **$XX.XX** |

---

## Sensitivity Analysis

### WACC vs Terminal Growth Rate

| WACC ↓ / g → | 1.5% | 2.0% | 2.5% | 3.0% |
|--------------|------|------|------|------|
| 8.0% | $XX | $XX | $XX | $XX |
| 8.5% | $XX | $XX | $XX | $XX |
| 9.0% | $XX | $XX | **$XX** | $XX |
| 9.5% | $XX | $XX | $XX | $XX |
| 10.0% | $XX | $XX | $XX | $XX |

### Key Drivers Impact

| Assumption Change | Impact on Value |
|-------------------|-----------------|
| WACC +1% | -XX% |
| Terminal Growth +0.5% | +XX% |
| Revenue CAGR +2% | +XX% |
| EBITDA Margin +2% | +XX% |

---

## Risks to Valuation

1. **Model Risk**: DCF highly sensitive to WACC and terminal growth assumptions
2. **Execution Risk**: Projected growth may not materialize
3. **Market Risk**: Multiple compression in downturn
4. **[Company-Specific Risk]**: [Detail]

---

## Disclaimer

This valuation model is for educational and informational purposes only. It does not constitute investment advice. The intrinsic value estimate is based on assumptions that may not reflect reality.

Example

User Request

Build a DCF model for a SaaS company with:
- Current revenue: $500M
- Revenue growth: 25% declining to 15% over 5 years
- EBITDA margin: 20% improving to 30%
- Current stock price: $45
- Shares outstanding: 100M

My Response

[Complete DCF model with all calculations...]


Tips for Better Results

  1. Provide historical data for more accurate projections
  2. Be explicit about growth assumptions rather than using defaults
  3. Specify the industry for appropriate comparables
  4. Request sensitivity analysis to understand valuation range
  5. Cross-check with multiples (P/E, EV/EBITDA) for sanity check

Limitations

  • Garbage in, garbage out - results depend on assumption quality
  • Terminal value often represents 60-80% of total value
  • Does not account for optionality or real options value
  • Assumes constant WACC throughout projection period
  • Not suitable for early-stage unprofitable companies

Built by the Claude Office Skills community. Contributions welcome!

Frequently asked questions

What does the Dcf Valuation AI skill do?

Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.

Why use Dcf Valuation on TypingMind?

Because you install it once and use it with any model. Dcf Valuation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dcf Valuation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/claude-office-skills/skills/tree/main/dcf-valuation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dcf Valuation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dcf Valuation?

As many as you like. As long as a model supports skills, you can use Dcf Valuation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dcf Valuation AI skill free?

Yes. It is published on GitHub by claude-office-skills under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇