Dcf valuation
Claude Code pack for financial analysts: data-integrity (citation), SEC/FINRA disclaimer, projection-labeling & MNPI/PII guardrails + skills for statement analysis, ratios, DCF/comps valuation, modeling, earnings, forecasting & FP&A, loops & review agents. Not investment advice.
npx -y skills add m-binimran/finance-pack --skill dcf-valuationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Build a discounted cash flow valuation - project free cash flow, discount at WACC, add terminal value, and run sensitivity. Use when estimating intrinsic value. Output is an estimate, not a fact.
SKILL.md
1.5 KB, as published. Nobody here has run it
dcf-valuation
Intrinsic value from projected cash flows - only as good as its assumptions, so expose them.
Process
- Historicals (sourced): revenue, margins, capex, working capital, tax rate from the filings.
- Project unlevered FCF over an explicit horizon (5-10y): revenue growth -> EBIT -> NOPAT -> + D&A
- capex - change in NWC. State each assumption.
- WACC: cost of equity (CAPM: risk-free + beta x ERP) and after-tax cost of debt, weighted. Show inputs.
- Terminal value: Gordon growth (perpetuity g) or exit multiple - sanity-check both; TV often dominates.
- Discount FCFs + TV to PV; bridge enterprise value -> equity value -> per share (net debt, shares).
- Sensitivity: a WACC x growth (and TV) table - give a value RANGE, not a single number.
Output
- The model assumptions, the FCF build, WACC, terminal value, the implied value RANGE per share, and the sensitivity table. Labeled an estimate with assumptions stated.
Guardrails
- Forward figures are projections - label them, state assumptions (
projection-guard/projections-assumptions). - Re-derive the math (DCFs are multi-step - AI errs); historicals sourced; report a range, not false precision.
- Not a recommendation without a disclaimer (
no-investment-advice).