What does this skill do, and when should you use it?
This skill guides the AI in creating professional comparable company analyses that combine operating metrics, valuation multiples, and peer benchmarking, producing a structured Excel spreadsheet to support investment decisions. It emphasizes building the right structure first, then letting data tell the story through transparent formulas and automatically generated statistics. The skill adapts metric selection based on industry context, audience, and decision type, and includes best practices for data sourcing, audit trails, and quality checks.
Collects financial data for peer companies (e.g., via fundamentals MCP tools), builds an Excel model with operating metrics (revenue, growth, margins) and valuation multiples (EV/Revenue, P/E), calculates distribution statistics (max, quartiles, median), requires source comments on all hard-coded cells, and guides the user through data gathering, formula building, quality control, and documentation steps.
- An M&A analyst benchmarks acquisition targets against peers to triangulate a fair value range.
- An equity researcher prepares a peer comparison for an investment committee to justify a rating.
- A portfolio manager evaluates which companies in a sector are the most operationally efficient.
- A growth investor compares SaaS companies using Rule of 40 and FCF margins.
- A credit analyst compares leverage and coverage ratios across issuers.
How do you install this skill?
- This skill is aimed at financial analysis and requires user background; its methodology relies on external data sources (e.g., MCP, SEC), which may be limited when overseas services are unreachable.
- The skill is static instructions without tests or validation; actual effectiveness should be verified by the user.
- No version history or maintenance responsibility is included; users should monitor repository updates.
- Shell / CLI
- Network access
- Local filesystem
PythonExcel
Obtain the skill from the LangAlpha repository (path skills/comps-analysis/SKILL.md), and place the SKILL.md file (or the containing folder) into your Agent's skills directory, typically under a 'skills' or '.agents/skills' folder in your workspace.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/ginlix-ai/LangAlpha.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/skills/comps-analysis" ~/.claude/skills/
rm -rf "$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:
- Run a comparable company analysis on [list of companies]
After installation, activate the skill and start a conversation with a prompt like: 'Run a comparable company analysis on [list of companies]'. Provide context on the audience and key question. The agent will guide you through data collection, building the Excel model, adding statistics and source comments, and delivering a reviewed analysis.
What are this skill's strengths and limitations?
- Comprehensive workflow covering structure, data, formulas, and documentation.
- Strong emphasis on transparency and audit trails with mandatory source comments.
- Provides industry-specific metric selection guidance (SaaS, manufacturing, etc.).
- Includes statistical benchmarks (quartiles, median) for relative valuation.
- Clear guidance on avoiding common mistakes like mixing market cap and EV.
- Requires some financial knowledge to use effectively.
- Depends on an external xlsx skill for formatting conventions.
- No automated test suite; quality relies on manual checks.
- Does not natively generate PDF reports; requires extension if needed.
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 |
|---|---|---|---|---|
| Comps Analysis Skill this page | 48 · Use with care | ★ 1.8k | 3d ago | Apache-2.0 |
| Comparable Company Analysis Modeling Skill ✓ Anthropic · Official | 52 · Use with care | ★ 39k | 20d ago | Apache-2.0 |
| Taiwan Stock One-Click Financial Model & Investment Deck Generator | 45 · Not recommended | ★ 40 | 3mo ago | — |
| Financial Model Refresh ✓ Anthropic · Official | 47 · Use with care | ★ 39k | 20d ago | Apache-2.0 |
| Three-Statement Model Builder ✓ Anthropic · Official | 55 · Use with care | ★ 39k | 20d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill itself is purely instructional documentation, with no execution permissions or behavior. It references external tools (fundamentals MCP, SEC) and advises audit trails, making it transparent. However, references to code execution (e.g., recalc.py) are in other files, not confirmed here. No dangerous overreach or recommendation detected, but external effects cannot be statically verified. Deductions: no permission or isolation mechanisms, being a pure instruction skill, so trust is moderate-low.
The skill is self-consistent with clear formulas and steps, but no tests or failure handling are present, and static review cannot verify actual execution. Thus 7 out of 10 for static review, deducted for non-reproducibility and lack of error handling.
The skill fits financial analysis scenarios, with clear objectives and metric selection frameworks, and includes non-fit ranges (e.g., excluding non-comparable companies). It does not explicitly address Chinese environment adaptation or data source reachability. Relies on external tools that may be constrained, but core methodology is unaffected. Hence 11 out of 15, deducted for lack of explicit non-fit boundaries and weak environment evidence.
The file has clear title and description, structured sections, examples, and checklists, but lacks version history, maintenance responsibility, and troubleshooting guidance. No update path mentioned. Thus 10 out of 15, deducted for missing governance information.
Provides detailed guidance, likely to produce structured Excel reports, but no real output verified, only static reading. Thus 6 out of 7, deducted for lack of representative output and usage effectiveness proof.
Lacks tests or independent execution evidence. Only script references, not statically confirmable. Thus 4 out of 5, deducted for lack of reproducibility evidence.
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 →