- Home
- Skills
- Finance & Accounting
- comps valuation workbook
More screenshots
Works with the AI Agents you already use
comps valuation workbook
Peer CSV to trading comps: EV/Revenue, EV/EBITDA, P/E, IQR outliers, implied share price range and a live-formula Excel file.
$9
comps valuation workbook
Example session with this skill installed
Value Harborline Software against these 6 SaaS peers. I need a range per share and a spreadsheet my partner can edit.
- Read your context and instructions
- Compiled the comps valuation workbook
Answer: about $9-$25 per share, blended midpoint $17.78, which is 3% below the current $18.40.
- Comps: EV/Revenue median 3.5x (2.5x-4.3x), EV/EBITDA 20.9x (12.1x-28.7x), P/E 33.2x (22.5x-48.5x)
Outlier removed: Gulfstream Logic (11.4x revenue, 173x EBITDA, 891x P/E) by the IQR rule.
NM: Tidewater's P/E (net loss)
Implied per share (net debt $35M, 52M shares): EV/Revenue $14.45 /
$20.38 / $25.08; EV/EBITDA $9.99 /
$17.78 / $24.71; P/E $9.08 /
$13.42 / $19.60
- EV/EBITDA is the most relevant method here (profitable, mid-growth). Revenue multiples flatter it, and P/E is pulled down by thin margins
Deliverables: comps.xlsx (live formulas, freeze-panes header, Include toggles), terminal football field, comps.json.
Next steps: confirm every figure is the same LTM period, then test removing Bluepeak (highest P/E) with its Include cell.
(Real run on the bundled sample peers. Not investment advice.)
Connects securely to your tools. The creator never sees your data.
About this skill
A banker-style comps table in one command, plus a workbook that still works when you change the numbers.
Give it a CSV of peers and the company you're valuing (role=target). It accepts the way people really type numbers: 52m, 1.45b, $1,450, (12m).
It computes:
- market cap and enterprise value (EV = market cap + debt − cash)
- EV/Revenue, EV/EBITDA, P/E, with negative denominators marked NM instead of producing silly negative multiples
- outliers removed with the IQR rule (and named, so you can defend it)
- 25th / median / 75th / mean per multiple
- implied value per share for each method, bridging EV to equity through net debt, plus a text football field and a blended midpoint vs the current price
Then it writes comps.xlsx with live formulas: every market cap, EV, multiple, QUARTILE/MEDIAN and implied value is an Excel formula. Change a price or flip a peer's Include cell to 0 and the whole sheet recalculates in Excel, Google Sheets, Numbers or LibreOffice. It's built with the Python standard library only (no openpyxl or pandas to install). Checked in LibreOffice: the sheet matches the script to the cent.
Good for startup and SMB valuations, acquisition targets, stock pitches, MBA and CFA case work.
What's included
SKILL.md, scripts/comps.py, sample SaaS peer set, method reference, sources (Damodaran, CFA curriculum, ECMA-376, Microsoft QUARTILE.INC), tests.
- Garbage in, garbage out: you supply and period-match the figures (LTM vs NTM).
- Covers EV/Revenue, EV/EBITDA and P/E; no DCF or precedent transactions.
- Debt should include leases, preferred and minority interest if material; add them to the debt column.
- Not investment advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 26 days ago
Permissions
File Scopes
Fully offline. Scripts never import networking or subprocess modules, never read environment variables and never use eval/exec. No market data is fetched; figures come from the user's CSV.