agentsclimarketplace

Comps valuation

Skill m-binimran/finance-pack/skills/comps-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.

Install
npx -y skills add m-binimran/finance-pack --skill comps-valuation

Assembled 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

Value a company by comparable companies / trading multiples (and precedent transactions) - select peers, compute multiples, and apply to the target. Use for relative valuation alongside a DCF.

SKILL.md

1.4 KB, as published. Nobody here has run it

comps-valuation

Relative value from how the market prices similar businesses. The peer set is everything.

Process

  1. Select peers: genuinely comparable by business model, size, growth, margins, geography - justify each; note where the target differs.
  2. Compute multiples for each peer (sourced): EV/Revenue, EV/EBITDA, P/E, P/FCF; use the right metric for the sector. Use a consistent basis (TTM or forward; EV reconciled with net debt).
  3. Benchmark: the peer median/mean and range; adjust for the target's growth/margin/quality differences.
  4. Apply the chosen multiple(s) to the target's metric -> implied EV/equity/per-share value RANGE.
  5. Precedent transactions (optional): control-premium multiples from comparable M&A.

Output

  • The peer table (multiples, sourced), the chosen multiple + rationale, and the implied value RANGE - plus how it triangulates with the DCF (a "football field").

Guardrails

  • Multiples sourced; consistent TTM/forward and EV basis (accuracy-precision); peers justified, not cherry-picked.
  • A range, not a point; combine with DCF rather than relying on one method (methodology).

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.