Comparable Company Valuation
Build institutional-grade peer valuation analyses with operating metrics, trading multiples, and statistical benchmarks in spreadsheets.
The skill specifies institutional MCP priority, prohibits web search when those sources exist, requires source documentation, and the README stages work for professional review. Deductions apply because least-privilege permissions, sensitive financial-data handling, connector authorization, rollback, and isolation controls are not defined.
The document is detailed and largely self-consistent, covering sources, formulas, statistics, quality checks, and abnormal-result checks. Static materials contain no skill-specific tests, reproducible artifact, or clear dependency-failure diagnostics, so the score remains conservative.
Use cases, non-fit company types, industry-specific metrics, and initial clarification questions are explicit, giving the skill a reasonably clear trigger boundary. Deductions apply because Chinese-language behavior and mainland-China reachability are not addressed, while MCP, Bloomberg, and Excel/Python availability may constrain deployment.
The documentation is well organized and includes an example layout, methodology, and quality checklist; repository context supplies Apache-2.0 licensing, official provenance, CI validation, and contribution/update guidance. Deductions apply because the skill lacks its own version, changelog, explicit installation dependencies, named maintenance owner, and troubleshooting guidance; the referenced example file was not verifiable from the supplied material.
The skill clearly targets a structured Excel/spreadsheet deliverable with formulas, statistics, source comments, and quality checks, so the core value proposition is credible. Static review cannot verify actual file generation, formula correctness, or end-to-end usability; human review remains necessary, so the static ceiling applies.
The instructions require source, period, cross-check, and cell-level attribution, while repository CI provides limited governance evidence. Deductions apply because there are no skill-specific tests, generated artifacts, or third-party execution results; key claims remain primarily documentary.
- Before use, confirm connector availability, subscription/API permissions, and the Excel or Python/openpyxl environment, including stable reachability from mainland China.
- Qualified professionals should review financial data, valuation assumptions, formulas, and statistics; the skill provides no automated rollback, sensitive-data isolation, or end-to-end tests.
- Add a skill version, changelog, dependency-failure handling, Chinese-output guidance, and reproducible examples.
What it does & when to use it
This skill guides the creation of comparable company analysis spreadsheets covering operating metrics, valuation multiples, and peer statistics. It prioritizes institutional data sources and requires derived values to use formulas that reference input cells. The workflow also addresses peer selection, reporting periods, units, source documentation, and sanity checks. It is designed for public-company valuation, peer benchmarking, IPO or financing pricing, and investment committee support.
It guides users to define the peer group, period, units, and analytical question before building the spreadsheet. It structures fields such as revenue, revenue growth, gross profit, gross margin, EBITDA, EBITDA margin, market capitalization, enterprise value, EV/revenue, EV/EBITDA, and P/E. It calculates derived metrics with spreadsheet formulas, adds maximum, quartile, median, and minimum statistics for comparable measures, and documents the source or assumption for each hard-coded input. The intended output is a structured Excel or spreadsheet analysis.
- An investment banker builds a peer valuation table for a public-company M&A process.
- An investment team compares industry companies by growth, margins, and trading multiples.
- An underwriting or financing team prepares valuation benchmarks for an IPO or funding round.
- An investment committee needs a formula-driven peer analysis with source notes and distribution statistics.
- A research team builds sector-specific comps for software, financial services, industrials, or retail companies.
Pros & cons
- Covers operating metrics, valuation multiples, distribution statistics, and methodology notes.
- Emphasizes transparent formulas, cross-references, and source audit trails.
- Provides metric-selection frameworks for software, financial services, industrials, and retail.
- Includes data-quality, valuation-reasonableness, and comparability checks.
- Not suited to companies without public peers, highly diversified companies, distressed or bankrupt companies, or pre-revenue startups.
- Financial data depends on access to institutional sources or other primary sources; the material does not establish that every connector is available in every environment.
- The skill text provides no test suite, execution results, or standalone package.
- Its focus is Excel or spreadsheet analysis, not investment advice or automated trading decisions.
How to install
The skill is bundled in the repository's Pitch Agent plugin. Following the README, run claude plugin marketplace add anthropics/financial-services, then claude plugin install pitch-agent@claude-for-financial-services. You can also install the core plugin with claude plugin install financial-analysis@claude-for-financial-services. The source does not document a standalone installation command for this individual SKILL.md.
How to use
After installation, use /comps in the Claude environment, or request an analysis such as “Build an institutional-grade comparable company analysis for [companies].” Provide the peer companies, period, currency or units, and the key analytical question. The skill calls for staged confirmation of the structure, raw inputs, operating formulas, and valuation multiples. No standalone CLI or API invocation is documented.