deal-screening
Deal Screening
Buy-side consultants, PE associates, and corporate development teams waste critical evaluation hours manually stripping corporate jargon from CIMs to find core data. This skill automates target screening and IOI generation.
When to Use
- Evaluating an inbound CIM or teaser from a sell-side bank
- Screening multiple targets simultaneously for a buy-side mandate
- Generating a customized IOI for an attractive target
- Building a rapid valuation view before investment committee review
The /cim-extract Protocol
How It Works
Deliberately bypasses CIM formatting entirely. Instructs the AI to ignore narrative prose and extract only:
- Quantitative assertions: Revenue, EBITDA, margins, growth rates, customer metrics
- Explicit strategic claims: Market position, competitive moats, expansion vectors
- Management adjustments: Proposed EBITDA add-backs with stated rationale
- Key risk indicators: Customer concentration, churn rates, capex requirements
Output Format
## CIM Extraction Summary — [Target Name]
### Financial Snapshot
| Metric | FY-2 | FY-1 | LTM | Mgmt Projection |
|--------|------|------|-----|-----------------|
| Revenue | | | | |
| Gross Margin | | | | |
| Adj. EBITDA | | | | |
| EBITDA Margin | | | | |
| Free Cash Flow | | | | |
### Proposed EBITDA Adjustments
| Add-Back | Amount | Rationale | Defensibility |
|----------|--------|-----------|---------------|
| | | | High / Medium / Low |
### Key Metrics
- **Customer concentration**: Top 10 = [X]% of revenue
- **Churn rate**: [X]%
- **CAC / LTV ratio**: [X]
- **Organic growth rate**: [X]%
### Investment Highlights (seller's claims)
1. [Claim] — [Supporting data point or "UNSUBSTANTIATED"]
### Red Flags
- [Identified concerns from the data]
### Verdict
[Quick BUY-SIDE assessment: Advance / Further Diligence / Pass]
IOI Memorandum Generation
Key Sections
| Section | Focus |
|---|---|
| Purchase Price Range | Enterprise valuation estimate, expressed as EBITDA multiple |
| Transaction Structure | Asset vs. stock, cash/equity/rollover/earn-out mix |
| Sources of Financing | Proof of funds, committed equity, anticipated leverage |
| Key Assumptions | Metrics the valuation relies upon |
| Due Diligence Scope | Remaining access required to reach definitive agreement |
| Timing & Approvals | Timeline to LOI and investment committee requirements |
AI-Assisted IOI Workflow
- Ingest the target's CIM and the buyer's investment committee memos
- Map buyer's strategic rationale to seller's growth pillars
- Generate bespoke IOI that feels tailored (not a form letter)
- Align the offer structure directly with CIM's identified opportunities
Operating Guidelines
- Never trust sell-side EBITDA at face value — always flag adjustments for validation
- Distinguish between organic and inorganic (M&A-driven) revenue growth
- Flag customer concentration above 20% for any single customer
- For IOIs, ensure the valuation range is defensible with stated methodology
- Time saved: 3-5 hours per CIM screening; IOI drafting gives massive competitive advantage in auctions
Examples
Input: "Screen this CIM. Key criteria: >$20M EBITDA, >70% gross margin, <12x EV/EBITDA."
Screening output:
| Criterion | Target | Finding | Pass/Fail |
|---|---|---|---|
| EBITDA | >$20M | $23.4M (adj.) | ✅ Pass |
| Gross margin | >70% | 68% | ❌ Fail |
| EV/EBITDA (ask) | <12x | 14.5x implied | ❌ Fail |
| Customer concentration | <20% top customer | Top customer = 31% | ⚠️ Flag |
Recommendation: Pass. Gross margin and valuation both miss. Note concentration risk for future reference.
Troubleshooting
| Problem | Cause | Fix |
|---|---|---|
| CIM doesn't disclose key metrics | Sell-side omission | Flag gaps in screening report; request data room access or submit IOI with conditions |
| Adjusted EBITDA looks inflated | Aggressive add-backs | Challenge non-recurring items; apply QoE discount pending diligence |
| Too many deals passing screening | Criteria too loose | Tighten thresholds or add negative criteria (e.g., "no government revenue >30%") |
More from lauraflorentin/skills-marketplace
multi-agent-collaboration
A structural pattern where multiple specialized agents communicate and coordinate to solve a problem that is too complex for a single agent. Use when user asks to "build a multi-agent system", "agents working together", "agent collaboration", or mentions team of agents, distributed agents, or swarm.
21reflection
A recursive pattern where an agent evaluates and critiques its own output to iteratively improve quality and catch errors. Use when user asks to "add self-reflection", "agent introspection", "self-critique", or mentions self-evaluation, meta-cognition, or quality self-assessment.
18human-in-the-loop
A hybrid pattern where the system pauses execution to request human approval, input, or disambiguation before proceeding with critical actions. Use when user asks to "add human approval", "require human review", "human-in-the-loop", or mentions approval workflows, human oversight, or escalation.
16planning
A high-level cognitive pattern where an agent formulates a structured sequence of actions (a plan) before executing any of them, ensuring goal-directed behavior. Use when user asks to "add planning to my agent", "task planning", "agent planning", or mentions plan generation, plan execution, or step-by-step planning.
14parallelization
A concurrency pattern where multiple agent tasks are executed at the same time to speed up processing or gather diverse perspectives. Use when user asks to "run agents in parallel", "parallelize tasks", "concurrent execution", or mentions parallel processing, fan-out, or batch execution.
13routing
A control flow pattern where a central component classifies an input request and directs it to the most appropriate specialized agent or tool. Use when user asks to "route between agents", "agent routing", "task dispatch", or mentions classifier routing, intent detection, or agent selection.
12