Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsQuick-Screen Scorecard
Score any acquisition opportunity across nine criteria the moment a teaser or CIM lands, and get a pursue / hold / pass verdict out of 18.
$5
Quick-Screen Scorecard
Example session with this skill installed
Use the Quick-Screen Scorecard on the attached Project Sentinel CIM (24 pages), financial statements (5 pages) and my call notes (1 page). Page numbers are printed footers.
My buy-box: recurring, compliance-driven field services; EBITDA between $1.0M and $2.0M; retiring founder; no asking price has been given yet.
- Read your context and instructions
- Compiled the quick-screen scorecard
Quick-Screen Scorecard: Project Sentinel
Scale 0 = poor, 1 = acceptable, 2 = strong. "Unknown" is not scored.
| Criterion | Score | Evidence |
|---|---|---|
| Thesis fit | 2 | Code-mandated inspection and service (CIM p.5), founder is the seller (CIM p.2). Region is not named in the materials. |
| Size fit | 2 | Reported EBITDA $1.08M, adjusted $1.42M (FS p.4), both inside $1.0M to $2.0M. |
| Revenue quality | 1 | 78% "recurring" but defined to include repair and call-out for contracted accounts (CIM p.22). No contract terms in materials. |
| Margin & cash health | 1 | Reported EBITDA is 17.4% of $6.21M, adjusted 22.9% (mine). No cost detail, cash flow or balance-sheet amounts (FS p.3 lists categories only). |
| Customer diversification | 0 | Northgate is about 22% (CIM p.9), top five 48.8% (mine), top ten about 61%. The CIM's own "no customer above 15%" is wrong (CIM p.8). |
| Owner independence | 0 | All work under the founder's personal licence (CIM p.14); founder leads day to day (CIM p.13). |
| Growth durability | 1 | $5.34M to $5.78M to $6.21M (FS p.2): +8.2%, +7.4% (mine, years undated). CIM attributes it partly to price (CIM p.6). |
| Price sanity | Unknown | No asking price in the materials. |
| Red-flag load | 0 | Concentration, licence dependence, 31.5% add-back load (mine), untested data export (CIM p.16), unreviewed change of control (CIM p.19). |
Total: 7 out of 16 assessable points (the price criterion is unknown, so the maximum is 16, not 18).
Verdict
Hold and dig, on the edge of pass. The bands are 13+ pursue, 8 to 12 hold, under 8 pass. If the unknown price is scored 1, the total is 8 (hold). If it scores 0, the total is 7 (pass). Do not spend a week on it; spend one call.
The single fact that would most change the result
The asking price. It moves one criterion by up to 2 points and decides which side of the band the deal lands on. It will not fix the three zeros, which sit in the documents.
Next step: ask the broker for the price expectation and for Northgate's contract term before any further work.
This screen is an analytical aid and not investment, legal, tax or accounting advice. The Project Sentinel documents are synthetic test data. Thresholds are a starting point; tune them to your own buy-box.
Connects securely to your tools. The creator never sees your data.
About this skill
Score any acquisition opportunity across nine criteria the moment a teaser or CIM lands, and get a pursue / hold / pass verdict out of 18. Use to triage deals fast, when asked to 'screen this deal', 'is this worth my time', 'score this opportunity', or to pass bad deals in minutes instead of weeks.
Works with
Any agent that reads the SKILL.md standard and can read attached documents. No scripts, no network access, no installs.
Known limitations
It works only from the documents you provide and cannot verify anything outside them. Analysis, not investment, legal, tax or accounting advice; check the output against the source documents.
About the author
Original work, listed by its author: part of the free, MIT-licensed open-deal-kit,
https://github.com/MariusGithub13/open-deal-kit
The hosted version that writes a fully cited diligence brief across a whole data room is Deal OS:
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 4 days ago
- Passed all security checks, Safe to install