deal-screening — Claude Code skill: what it does, how to install
Screens inbound CIMs, teasers, and broker materials against a fund’s criteria. Useful for triaging deal flow before a first call.
npx skills add anthropics/financial-services --skill deal-screening -a claude-codeWhat deal-screening does
deal-screening pulls the main facts from a CIM, teaser, or deal description: company, sector, location, financials, deal type, valuation, seller motivation, management, customer concentration, and obvious risks. It then compares the deal with the fund’s criteria, including revenue, EBITDA, margins, growth, geography, deal size, valuation, and management continuity.
The output is a one-page screening memo for partners or an investment committee quick screen. It includes a Pass, Further Diligence, or Hard Pass verdict, bull and bear points, plus questions for a first call. The skill also flags financials that look incomplete or inconsistent.
When the fund’s criteria are not known, the skill asks for them first. That means the criteria should be ready before screening if you want the comparison to cover the target ranges.
What it helps with
- extract key facts from an inbound CIM
- compare a deal with the fund’s criteria
- spot customer concentration and obvious red flags
- prepare a one-page screening memo
- draft questions for a first call
Example prompts for the agent
- Screen this CIM against our fund criteria and give me a deal verdict.
- Triage this teaser, extract the financials, and assess whether we should take a first call.
- Create a one-page screening memo with the bull case, bear case, and key questions.
How to install deal-screening
1Skills CLI (Vercel)
npx skills add anthropics/financial-services --skill deal-screening -a claude-code2Manually: put the files in place
~/.claude/skills/deal-screening/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/deal-screening/
1Skills CLI (Vercel)
npx skills add anthropics/financial-services --skill deal-screening -a codex2Manually: put the files in place
.agents/skills/deal-screening/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/financial-services --skill deal-screening -a cursor2Manually: put the files in place
.cursor/skills/deal-screening/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/financial-services deal-screening2Manually: put the files in place
.github/skills/deal-screening/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/financial-services --skill deal-screening -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/financial-services --path plugins/vertical-plugins/private-equity/skills/deal-screeningManually: put the files in place
.devin/skills/deal-screening/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add anthropics/financial-services --skill deal-screening -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set51
The whole set →Similar
Questions about deal-screening
How do I install deal-screening in Claude Code?
Run npx skills add anthropics/financial-services --skill deal-screening -a claude-code, then run npx skills add anthropics/financial-services --skill deal-screening -a claude-code again. The skill file is at ~/.claude/skills/deal-screening/SKILL.md.
What does deal-screening do?
It extracts deal facts from CIMs, teasers, and broker materials, checks them against fund criteria, and produces a one-page memo with a verdict, upside points, risks, and first-call questions.
What happens when the fund’s criteria are not known?
The skill asks for the fund’s criteria before screening. These can cover revenue and EBITDA ranges, margin, growth, geography, deal size, valuation, customer concentration, and management continuity.
Source text
SKILL.md · Apache-2.0
--- name: deal-screening description: Quickly screen inbound deal flow — CIMs, teasers, and broker materials — against the fund's investment criteria. Extracts key deal metrics, runs a pass/fail framework, and outputs a one-page screening memo. Use when reviewing new deal flow, triaging inbound materials, or deciding whether to take a first call. Triggers on "screen this deal", "review this CIM", "should we look at this", "triage this teaser", or "deal screening". --- # Deal Screening ## Workflow ### Step 1: Extract Deal Facts From the provided CIM, teaser, or description, extract: - **Company**: Name, location, sector/subsector - **Description**: What they do (1-2 sentences) - **Financials**: Revenue, EBITDA, margins, growth rate - **Deal type**: Platform, add-on, recap, minority, carve-out - **Asking price / valuation**: Multiple, enterprise value if stated - **Seller motivation**: Why selling now - **Management**: Rolling or exiting - **Key customers**: Concentration risk - **Key risks**: Obvious red flags ### Step 2: Screen Against Criteria Apply the fund's investment criteria (ask user if not known): | Criterion | Target | Actual | Pass/Fail | |-----------|--------|--------|-----------| | Revenue range | | | | | EBITDA range | | | | | EBITDA margin | | | | | Growth profile | | | | | Sector fit | | | | | Geography | | | | | Deal size / EV | | | | | Valuation (x EBITDA) | | | | | Customer concentration | | | | | Management continuity | | | | ### Step 3: Quick Assessment Provide a 3-part assessment: 1. **Verdict**: Pass / Further Diligence / Hard Pass 2. **Bull case** (2-3 bullets): Why this could be a good deal 3. **Bear case** (2-3 bullets): Key risks and concerns 4. **Key questions**: What you'd need to answer on a first call ### Step 4: Output One-page screening memo suitable for sharing with partners or an IC quick screen. ## Important Notes - Speed matters — screening should take minutes, not hours - Be direct about red flags. Don't bury concerns - If financials seem inconsistent or incomplete, flag it explicitly - Ask for the fund's criteria upfront if this is the first screening - Save screening criteria in memory for future deals once confirmed
© anthropics · Apache-2.0 · anthropics/financial-services