What does this skill do, and when should you use it?
This skill guides the creation of structured comparable company analyses covering operating metrics, valuation multiples, and peer statistics. It emphasizes defining the peer group and reporting period, documenting raw-data sources, and calculating derived values with spreadsheet formulas. The intended output is an auditable spreadsheet rather than an unsupported valuation conclusion. It is suited to public-company valuation, peer benchmarking, IPO or funding pricing, and investment-committee support.
Guides the user through selecting the analytical question, peer group, period, units, and industry-specific metrics; structures revenue, growth, gross profit, EBITDA, margins, market capitalization, enterprise value, and valuation multiples in Excel or a standalone .xlsx file; calculates margins, EV/Revenue, EV/EBITDA, P/E, and related metrics with formulas; adds maximum, quartile, median, and minimum statistics for comparable metrics; documents data sources, definitions, valuation methodology, assumptions, and quality checks; and requires staged confirmation of the structure, raw inputs, operating formulas, and valuation multiples.
- An investment banker or equity researcher needs to compare public-company valuations and support an investment-committee presentation.
- An M&A or investment team evaluates a target company and needs a valuation range based on public peers.
- A research analyst compares sector companies on growth, margins, operating efficiency, and trading multiples.
- An IPO or financing team uses peer multiples to identify premium, discount, and valuation outliers.
- A SaaS analyst benchmarks growth, gross margin, free-cash-flow margin, and Rule of 40 across comparable companies.
How do you install this skill?
- The core data workflow depends on external MCP, Bloomberg, or SEC access; confirm reachability, subscriptions, data rights, and mainland-China network availability before use.
- This skill produces investment-analysis work product, not investment advice; humans must verify periods, definitions, formulas, outliers, and valuation conclusions.
- The skill requests staged confirmation but does not define recovery, partial-completion, or sensitive-data cleanup procedures after failure.
- Network access
- Local filesystem
- MCP Server
Excel or Office JSPython/openpyxl for standalone .xlsx generationS&P Kensho MCP, FactSet MCP, or Daloopa MCP when available
In Cowork, open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and select market-researcher; or in Claude Code run: claude plugin marketplace add anthropics/financial-services, followed by claude plugin install market-researcher@claude-for-financial-services. The README does not document a standalone installation procedure for this individual SKILL.md file.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/anthropics/financial-services.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/agent-plugins/market-researcher/skills/comps-analysis" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Build a comparable company analysis for [companies], using [period] and [currency units]. Ask me to confirm the structure and data sources before proceeding.
After installation, invoke /comps, or use a request such as: "Build a comparable company analysis for [companies], using [period] and [currency units]. Ask me to confirm the structure and data sources before proceeding." Specify the audience, key question, industry context, and preferred spreadsheet format.
What are this skill's strengths and limitations?
- Covers operating metrics, valuation multiples, statistical distributions, and methodology documentation in one workflow.
- Requires derived values to use spreadsheet formulas and hard-coded inputs to carry source or assumption documentation.
- Provides metric-selection guidance for SaaS, financial services, industrials, retail, and other sectors.
- Includes data-source prioritization, cross-reference rules, sanity checks, and common-error guidance.
- The skill does not supply company data, valuation conclusions, or a pre-validated Excel workbook.
- It depends on an execution environment such as Excel/Office JS or Python/openpyxl, whose full setup is not documented.
- Institutional data sources may require provider subscriptions or API access.
- It is less suitable for private companies without public peers, distressed companies, conglomerates, and pre-revenue startups.
- The source material provides no test suite or platform validation results.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Comparable Company Analysis Modeling Skill this page ✓ Anthropic · Official | 52 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Comps Analysis Skill | 48 · Use with care | ★ 1.8k | 11d ago | Apache-2.0 |
| Model Checker for Financial Audits | 53 · Use with care | ★ 1.8k | 11d ago | Apache-2.0 |
| Investment Banking Strip Profile Builder ✓ Anthropic · Official | 47 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Taiwan Stock One-Click Financial Model & Investment Deck Generator | 45 · Not recommended | ★ 40 | 3mo ago | — |
The skill prioritizes S&P Kensho, FactSet, and Daloopa MCP sources for financial and trading information; when unavailable, it recommends Bloomberg Terminal, SEC EDGAR, or other institutional sources. It does not provide a direct feature comparison with other comparable-analysis products or templates.
How did FollowSkills review this skill?
The skill prioritizes institutional data sources, requires source comments and audit trails, and includes staged user confirmation; no malware, credential theft, or destructive behavior is evident. However, it relies on external MCPs, Bloomberg, and SEC access without specifying sensitive-financial-data handling, permission isolation, rollback, or cleanup on failure, so points are deducted.
The documented workflow, formula rules, and quality checks make the main path understandable. There are no skill-specific tests, reproducible execution results, or diagnostic abnormal-input failure procedures, and external data dependencies create environmental variance, so the score remains below the static ceiling.
Use cases, non-fit company types, industry metrics, and decision questions are clearly described, and the skill asks for format, audience, and objective context. Trigger conditions, input/output contracts, and non-English environment support are not precise; core MCP and terminal access may depend on mainland-China network reachability and subscriptions, so points are deducted.
The document has clear information architecture, progressive workflow guidance, formula conventions, QC checks, and an example layout; Apache-2.0 licensing and repository-level CI are also present. The skill lacks its own version, changelog, explicit maintainer/update path, dependency installation notes, and troubleshooting FAQ, so points are deducted.
The intended output, spreadsheet structure, formulas, and statistical methods are concrete and could complete the core comparable-company-analysis task. There is no file-contained third-party execution evidence, and data retrieval, workbook generation, and final formatting still require human review, so the score is capped by static calibration and reduced for uncertainty.
The skill requests source-level documentation, period disclosure, cross-checking, and formula audit trails, while repository workflows provide general plugin validation and secret scanning. It lacks dedicated tests covering the skill's key paths and independent reproduction evidence, so it receives only the static-review ceiling.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →