agentsclimarketplace
Sign in

Company valuation

Skill GAJETOso/financeskills/skills/company-valuation

When the user wants to value a mature company using DCF, trading comparables, or precedent transactions. Also use when the user mentions "intrinsic value," "DCF model," "terminal value," "EV/EBITDA multiple," "comps analysis," "football field," "enterprise to equity bridge," or "fairness opinion."From its SKILL.md

Install
npx -y skills add GAJETOso/financeskills --skill company-valuation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 10 stars10 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.
  • runs commandsInstructs the agent to run 1 command, including `python3 scripts/calculate.py`.

SKILL.md

3.8 KB, 821 tokens by cl100k_base, as published. Nobody here has run it

Company Valuation

You are a Valuation Analyst. Your goal is to triangulate enterprise and equity value using DCF, trading comparables, and precedent transactions — and to be explicit about which assumptions drive the answer.

Initial Assessment

  1. Valuation Context

    • Purpose: M&A, fairness, impairment testing, fundraising, PPA — purpose changes the standard of value (fair value vs. investment value vs. fair market value).
    • Control vs. minority basis; marketability considerations.

  2. Inputs Available

    • Historical financials (≥ 3 years), management projections, comparable set candidates, recent transactions in the sector.

Valuation Framework

Method 1: DCF

  1. Project unlevered FCF 5–10 years: EBIT × (1−t) + D&A − capex − ΔNWC.
  2. Terminal value: Gordon TV = FCFn×(1+g)/(WACC−g) with g ≤ long-run nominal GDP; cross-check with exit multiple — if the implied exit multiple looks unlike today's comps, your TV is doing too much work (TV > 75% of EV = warning).
  3. Discount at WACC (wacc-computation), mid-year convention if appropriate.
  4. EV-to-equity bridge: EV − net debt − preferred − minority interest + investments/associates ± pension deficit ± other debt-like items = equity value.

Method 2: Trading Comparables

Select 5–10 peers (business model > industry code); spread multiples (EV/EBITDA, EV/EBIT, P/E, sector-specific: EV/Revenue for high growth, P/B for banks, EV/2P for E&P); apply median and quartile range to the target's normalized metric; adjust for size/growth/margin gaps.

Method 3: Precedent Transactions

Same mechanics on deal multiples; embeds control premium (typically 20–35%); check deal context (synergistic buyer? distressed seller? auction?) and staleness.

Triangulation

Football-field chart of ranges; weight by input quality, not preference. DCF-vs-comps divergence > 30% means an assumption is wrong somewhere — find it, don't average it away.

Technical Analysis Steps

  1. Normalize first: strip one-offs (litigation, restructuring, FX swings, COVID-type distortions), pro-forma full-year acquisitions, normalize working capital.
  2. Build with code: FCF model, sensitivity grid (WACC × g, WACC × exit multiple), bridge waterfall.
  3. Sanity battery: implied multiples vs. comps, ROIC vs. WACC trajectory (value creation claim must be defensible), revenue growth vs. market growth + share math.

Output Format

Valuation Report

Summary: football field with concluded range and basis of value.

DCF: assumptions table, FCF build, TV cross-check, sensitivity grid.

Comps/Precedents: peer table with multiples, target metric normalization, applied range.

Bridge: EV-to-equity waterfall with every debt-like item itemized.

Key Judgments: the 3–5 assumptions that actually move the answer.

Scripts

  • calculate.py: Deterministic functions for this skill's core computations. Run python3 scripts/calculate.py to self-test; import the functions instead of doing mental math.

References

Related Skills

  • wacc-computation: The discount rate input.
  • financial-analysis: Ratio and trend work feeding normalization.
  • lbo-modeling: LBO analysis as a valuation floor check.
  • startup-valuation: For pre-revenue/high-growth targets instead of this skill.

What ships with it: 5 files

7.8 KB alongside SKILL.md, 1 of them executable

evals/

references/

scripts/

Gives 0 of the 12 instructions most finance skills give in 821 tokens

Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07

  • Extract date vendor amount and descriptionin 15 of 469, across 3 files
  • Scan folder for invoice filesin 14 of 469, across 2 files
  • Rename files to standard formatin 14 of 469, across 2 files
  • Show organization plan before movingin 14 of 469, across 2 files
  • Generate summary CSVin 14 of 469, across 2 files
  • Organize files by categoryin 13 of 469, across 1 file
  • Preserve original filesin 13 of 469, across 1 file
  • Flag files missing critical infoin 13 of 469, across 1 file
  • Produce the requested output filein 9 of 469, across 4 files
  • Build best, base, and worst case scenariosin 9 of 469, across 5 files
  • Implement backoff if rate limit errors occurin 8 of 469, across 3 files
  • Determine the weighted average cost of capitalin 8 of 469, across 4 files

Said here and by no other author read

  • import calculation functions for all math
  • cap terminal growth at long-run nominal gdp
  • cross-check terminal value with exit multiple
  • calculate equity value from enterprise value
  • select peers by business model
  • apply median and quartile ranges to target metrics

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. 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.