PromptsEdge
FreeGitHubData

Company Valuation Models

Your AI estimates a company's intrinsic value with DCF, peer multiples, and SOTP, blending them into an implied share price with upside/downside, sensitivity grids, and scenario analysis. Requires Python and yfinance.

Try asking: “Run a DCF and peer multiple valuation for NVDA with upside/downside”

himself65 on GitHub

Curated by PromptsEdge from a public repo · MIT license. All credit goes to the author.

What is this skill?

Knowing what a company is truly worth is the heart of fundamental investing. With this skill, your AI can build a full valuation model for any public company, combining discounted cash flow (DCF), peer multiple, and sum-of-the-parts (SOTP) analysis. It blends these methods into a single implied share price, complete with upside/downside, WACC and terminal growth sensitivity, and bull/base/bear scenarios. This is ideal for analysts, investors, and anyone who wants a research-grade valuation built from first principles, not just a price pulled from memory.

What you can do

  • Run a 5-year DCF model with explicit revenue, margin, WACC, and terminal growth assumptions (e.g., "AAPL DCF: $210/share, +12% upside").
  • Compare to peer multiples (P/E, EV/EBITDA, EV/Revenue) across 4-6 similar companies (e.g., "Peer median P/E: 24x, implied price: $198").
  • Break down value by segment using SOTP for conglomerates (e.g., "GOOG: Search $1.2T, Cloud $400B, Other Bets $50B").
  • Blend the three methods into a weighted implied price and show upside/downside vs market.
  • See a WACC × terminal growth sensitivity grid and scenario analysis (bull/base/bear cases).
  • Get a detailed report with key risks, caveats, and methodology notes.

How it works

Your AI pulls 5 years of financials and analyst estimates using yfinance, then builds a DCF with explicit cash flow, discount rate, and terminal value assumptions. It selects peers for relative valuation, calculates implied prices from multiples, and runs SOTP if the company has multiple segments. The results are blended, and a sensitivity matrix is generated to show how changes in WACC or terminal growth affect the implied price. The final output is a structured briefing with all calculations and context.

Good to know

  • Requires Python 3.8+ and the yfinance, numpy, and pandas packages (auto-installed if missing).
  • Works on CLI-based agents with shell and pip support.
  • No authentication or API keys needed.
  • Output is for research and education—never investment advice.

Related skills

View all →