comps-analysis

Build comparable company analysis spreadsheets with valuation multiples and peer benchmarking in Excel.

Updated Jun 7, 2026
One-click install
npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill comps-analysis-chensihakniroth
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: comps-analysis
Source: https://github.com/Chensihakniroth/ANAKOT-AGENT/tree/main/optional-skills/finance/comps-analysis
Command: npx skills add https://github.com/Chensihakniroth/ANAKOT-AGENT --skill comps-analysis-chensihakniroth

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openpyxl.

What problem does it solve? Building institutional-grade comparable company analyses manually is slow and error-prone, requiring careful formula construction, consistent formatting, and statistical benchmarking across peer sets. ## Core Features & Use Cases - Structured Excel Output: Generates .xlsx comps models via headless openpyxl with operating metrics, valuation multiples, and quartile statistics (Max, 75th, Median, 25th, Min). - Formula-Driven Models: Every derived value is a live Excel formula referencing input cells, with cell comments citing data sources or assumptions for full audit trails. - Data Source Discipline: Enforces a hierarchy prioritizing MCP financial data sources (S&P Kensho, FactSet, Daloopa), falling back to SEC EDGAR and web sources, never fabricating numbers. - Use Case: Ask the agent to compare Microsoft, Alphabet, and Amazon on revenue growth, EBITDA margin, EV/EBITDA, and P/E, and receive a formatted Excel workbook with statistics blocks and methodology notes. ## Quick Start Build a comparable company analysis in Excel for Microsoft, Alphabet, and Amazon using Q4 2024 data with operating metrics and valuation multiples.

Frequently Asked Questions about comps-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a comparable company analysis in Excel with Python?▼

Use openpyxl to write formula strings like =E7/C7 into cells rather than computed values, keeping the model live when inputs change. Structure the sheet with operating metrics, valuation multiples, and a statistics block using MEDIAN and QUARTILE functions.

What valuation multiples should a comps analysis include?▼

Core multiples are EV/Revenue, EV/EBITDA, and P/E, plus Market Cap and Enterprise Value. Add 2-3 industry-specific metrics like Rule of 40 for SaaS or ROE for financial services, following the 5-10 rule to avoid noise.

What data sources are best for institutional comps analysis?▼

Structured financial-data MCPs such as S&P Kensho, FactSet, or Daloopa are preferred for verified, auditable data. If unavailable, fall back to SEC EDGAR filings, company IR pages, or Bloomberg, and flag any unsourced numbers.

Does this skill work with live Excel or only headless files?▼

It targets headless openpyxl, producing an .xlsx file on disk rather than driving a live Excel session. The Office-JS live-Excel paths from the original plugin were removed; recalculation runs through the excel-author recalc script.

Why should comps models use formulas instead of hardcoded values?▼

Hardcoded derived values become silent bugs when inputs change, while formulas update automatically. Only raw input data should be hardcoded, and each input cell needs a comment citing its source or explaining the assumption.