Agent skill · Audited from source

deal-screening

skill · anthropics/financial-servicesApache-2.0 licenceAudited 28 Oct 2026 · source 06253c4f9534

★ 40,878pushed 36 days ago
✓SAFEGrade B · 89/100 · 28 Oct 2026 · 06253c4
40,878repo stars · whole anthropics/financial-services

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 06253c4f9534 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 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…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “deal-screening (anthropics/financial-services)”. Retrieved 28 Oct 2026. https://modelsatlas.com/skills/anthropics/deal-screening

Trust audit

Audit 0.4.1 · source read 28 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha 06253c4f9534 · 28 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheranthropics GitHub organizationOwner of the repository this skill is read from
  • Source folderanthropics/financial-services/plugins/vertical-plugins/private-equity/skills/deal-screeningThe exact folder we audited
  • LicenceApache-2.0As the repository states it
  • Commit pinned for this verdict06253c4f9534A new audit runs when the source changes
  • Repository statusNot archivedLast push 36 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its 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…

---
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

Excerpt, first 2,208 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 06253c4

Download folder ↗
git clone https://github.com/anthropics/financial-services
git -C financial-services checkout 06253c4f9534

The author documents no install command, so this uses the repository directly. Our verdict covers commit 06253c4f9534 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 06253c4f9534

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/deal-screening/badge.svg)](https://modelsatlas.com/skills/anthropics/deal-screening/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/anthropics/deal-screening/badge.svg)](https://modelsatlas.com/skills/anthropics/deal-screening/)

Questions about deal-screening

Is deal-screening safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can deal-screening access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (06253c4f9534), read on 2026-10-28. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.