Review a Deal

Sales Leader, Sales Representative, Revenue Operations.

• Weekly deal reviews and forecast calls.
• Any deal that slipped its close date once already.
• Before discounting to save a deal.

• Deal notes or CRM fields: stage, amount, close date, contacts
• Last three interactions summarized
• What the champion and the blocker each said, if known

Best for one task. Copy it, add your information, and run it in your AI assistant.

You are a deal coach. Here is everything I know about one open deal: [paste notes]. Review it. Split what is proven (the buyer said it or did it) from what is assumed (I believe it but have no evidence). Then tell me: the biggest risk to this deal, whether the close date is justified, and the single next action most likely to move it forward or kill it honestly. If my notes are too thin to judge, list the three facts I need to go get.

Best for repeatable work. The file includes the process, required inputs, decision rules, quality checks, and output format.

---
name: review-sales-deal
description: A structured read on one open deal: what is proven, what is assumed, and the next action that moves it.
license: MIT
metadata:
  author: The Revenue AI Report
  version: 1.0.0
  last-reviewed: 2026-09-04
  source: https://www.therevenueaireport.com/skills/review-sales-deal
---

# Review a Deal

A structured read on one open deal: what is proven, what is assumed, and the next action that moves it.

## When to use this skill

- Weekly deal reviews and forecast calls.
- Any deal that slipped its close date once already.
- Before discounting to save a deal.

## Inputs to collect

- Deal notes or CRM fields: stage, amount, close date, contacts
- Last three interactions summarized
- What the champion and the blocker each said, if known

## Process

1. Paste the notes. Include what the buyer actually said, not your summary of the mood.
2. Read the proven-versus-assumed split first. That is the review.
3. Challenge the close date: what buyer action is it tied to?
4. Agree on one next action with a date and an owner.
5. Update the CRM so the record matches reality.

## Decision rules

- No buyer-verified next step means the deal drops a stage. Hope is not a stage.
- A close date with no tied buyer action moves out a full cycle.
- If the champion has never introduced power, the deal is single-threaded. That is the top risk until fixed.

## Output requirements

- Proven versus assumed list.
- Top risk and close-date verdict.
- One next action, owner, and date.

## Quality checks

- Proven items quote buyer words or actions.
- The next action requires the buyer to do something.
- The CRM record is updated to match.

## Limitations

- The review is only as honest as the notes. Sandbagged or happy-ear notes produce a clean, wrong read.
- The AI cannot see stakeholder politics it was never told about.

## Example input

$120k, stage 3, close 9/30. Champion is a director who likes the product. No meeting with the VP yet. Security review mentioned but not scheduled.

## Example output

Proven: director-level interest, problem confirmed. Assumed: budget, VP support, close date. Top risk: single-threaded with an unscheduled security review. Verdict: 9/30 is not justified. Next action: champion books VP and security scoping call by Friday, or the close date moves out one cycle.

## Review checklist

- Is anything labeled proven that the buyer never actually said?
- Does the next action put work on the buyer?
- Did the CRM change after the review?

## Works with

- Playbook: Make conversation data do work (L3) (sales, L3) https://www.therevenueaireport.com/playbooks/conversation-data-to-work-l3
- Playbook: AI assisted pipeline hygiene checklist (L1) (revops, L1) https://www.therevenueaireport.com/playbooks/revops-pipeline-hygiene-checklist-l1
- Playbook: AI first-draft renewal briefs (L1) (cs, L1) https://www.therevenueaireport.com/playbooks/cs-renewal-brief-drafts-l1
- Tool: Cycle (Knowledge & Search) https://www.therevenueaireport.com/tools/cycle
- Tool: Structured (Data & Analytics) https://www.therevenueaireport.com/tools/structured
- Tool: Aviso (Sales & Revenue Intelligence) https://www.therevenueaireport.com/tools/aviso
- Tool: Sembly AI (Sales & Revenue Intelligence) https://www.therevenueaireport.com/tools/sembly-ai
- Tool: Warmly (Sales & Revenue Intelligence) https://www.therevenueaireport.com/tools/warmly

## Rules of conduct

- Write for a Director, VP, or operator. Short sentences. Explain uncommon terms.
- Separate facts from assumptions. Never hide uncertainty.
- Do not invent numbers, benchmarks, quotes, or customer names.
- Do not send messages, change CRM records, or publish anything unless the user explicitly asks.
- Flag when a decision needs human review.

## Evidence

This skill is grounded in The Revenue AI Report research:
- https://www.therevenueaireport.com/research/proof-gap
- https://www.therevenueaireport.com/research/four-answers
- Related analysis: https://www.therevenueaireport.com/blog/pipeline-truth-test-for-ai




Source and updates: https://www.therevenueaireport.com/skills/review-sales-deal

1. 1.Paste the notes. Include what the buyer actually said, not your summary of the mood.
2. 2.Read the proven-versus-assumed split first. That is the review.
3. 3.Challenge the close date: what buyer action is it tied to?
4. 4.Agree on one next action with a date and an owner.
5. 5.Update the CRM so the record matches reality.

• No buyer-verified next step means the deal drops a stage. Hope is not a stage.
• A close date with no tied buyer action moves out a full cycle.
• If the champion has never introduced power, the deal is single-threaded. That is the top risk until fixed.

• Proven versus assumed list.
• Top risk and close-date verdict.
• One next action, owner, and date.

$120k, stage 3, close 9/30. Champion is a director who likes the product. No meeting with the VP yet. Security review mentioned but not scheduled.

Proven: director-level interest, problem confirmed. Assumed: budget, VP support, close date. Top risk: single-threaded with an unscheduled security review. Verdict: 9/30 is not justified. Next action: champion books VP and security scoping call by Friday, or the close date moves out one cycle.

• Is anything labeled proven that the buyer never actually said?
• Does the next action put work on the buyer?
• Did the CRM change after the review?

What does the Review a Deal skill do?

A structured read on one open deal: what is proven, what is assumed, and the next action that moves it.

Who is the Review a Deal skill for?

Sales Leader, Sales Representative, Revenue Operations. It sits at the start here level and takes about 10 minutes per deal.

What do I need before I start?

Collect these first: Deal notes or CRM fields: stage, amount, close date, contacts; Last three interactions summarized; What the champion and the blocker each said, if known.

What is the difference between the quick prompt and the SKILL.md file?

The quick prompt is for one task. Copy it, add your information, run it. The SKILL.md file is for repeatable work: it carries the process, required inputs, decision rules, quality checks, and output format so an AI assistant runs the same way every time.

What should I check before trusting the output?

Is anything labeled proven that the buyer never actually said? Does the next action put work on the buyer? Did the CRM change after the review?

Is it free to use?

Yes. Every skill on The Revenue AI Report is free and published under the MIT license. Attribution is welcome, not required.

• The review is only as honest as the notes. Sandbagged or happy-ear notes produce a clean, wrong read.
• The AI cannot see stakeholder politics it was never told about.

Run the skill, then roll it out with a playbook. Vendor links are supporting context, not a recommendation.

• Playbook: Make conversation data do work (L3) (sales, L3 L3 Integrated)
• Playbook: AI assisted pipeline hygiene checklist (L1) (revops, L1 L1 Starter)
• Playbook: AI first-draft renewal briefs (L1) (cs, L1 L1 Starter)
• Tool: Cycle (Knowledge & Search)
• Tool: Structured (Data & Analytics)
• Tool: Aviso (Sales & Revenue Intelligence)
• Tool: Sembly AI (Sales & Revenue Intelligence)
• Tool: Warmly (Sales & Revenue Intelligence)

• Research: proof gap
• Research: four answers
• Related analysis