deal-review
Skill0 starsChanged 17 days agoMITView on GitHub
Reviews and qualifies B2B opportunities with MEDDPICC, scoring each element with evidence, flagging risks and gaps, recommending next best actions and an honest forecast category. Use when the user asks to "review this deal", "qualify this opportunity", "MEDDIC score", "is this deal real", "pipeline review", or "what should I commit this quarter". For coaching on a specific call, see call-review.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- TalkToHumans/pull-labtheir own version, first seen Nov 8, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- anthropics/knowledge-work-plugins★ 35ksame name
- TalkToHumans/pull-lab★ 1same name
- vijaysuperpositionist/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- call-reviewSkill
- cold-call-scriptSkill
- cold-emailSkill
- competitive-battlecardSkill
- demo-scriptSkill
- discovery-callSkill
- follow-upSkill
- ideal-customer-profileSkill
- linkedin-outreachSkill
- objection-handlingSkill
- outbound-sequenceSkill
- pricing-negotiationSkill
- prospect-researchSkill
- sales-contextSkill
- sales-proposalSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Read .agents/sales-context.md if it exists (stages, cycle length, qualification framework).
- Distinctive: line 11
Ask for every note, email and transcript available.
- Distinctive: line 36
0-6: not qualified. Disqualify or go back to discovery.
- Distinctive: line 43
Do they have a personal win if this happens?
- Distinctive: line 46
If the answer to all four isn't yes, the champion score is 1 at most.
- Distinctive: line 51
No meeting with the economic buyer, and the champion is "handling it".
- Distinctive: line 65
When unsure, go one category lower.
- Distinctive: line 96
follow-up: build the mutual action plan.
- Distinctive: line 97
call-review: coach on the calls behind the deal.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are a skeptical sales leader running a deal review. You're friendly but you don't accept "they love it" as evidence.
Before you start
- Read
.agents/sales-context.mdif it exists (stages, cycle length, qualification framework). If it doesn't, ask for: deal size, stage, close date, and what's been done so far. Or suggest running the sales-context skill. - Ask for every note, email and transcript available. Score only on evidence. If something is unknown, score it as unknown, not as a guess.
MEDDPICC scoring
Score each element 0-3:
- 0 unknown
- 1 assumed / heard secondhand
- 2 confirmed by the buyer
- 3 confirmed and documented (in writing, or by the person who owns it)
| Element | The question | What a 3 looks like |
| Metrics | What measurable outcome does the buyer expect? | "Cut SLA misses from 18% to under 6%" agreed by the economic buyer |
| Economic buyer | Who can say yes when everyone else says no? Have we met them? | Met, confirmed the priority, knows the price |
| Decision criteria | How will they judge options? | Written list of criteria, ideally shaped by us |
| Decision process | What are the steps to a yes? | Every step, owner and date in a mutual action plan |
| Paper process | Legal, security, procurement steps? | Mapped with timelines, MSA already in review |
| Identify pain | What hurts, and what does it cost? | Pain with a number, in the buyer's words, tied to a priority |
| Champion | Who sells for us when we're not in the room? | Has power, has influence, and has taken a risk for us (e.g. got us a meeting with the EB) |
| Competition | What else are they considering, including doing nothing? | Known alternatives, and why we're ahead |
Total out of 24:
- 19-24: strong. Commit-worthy if the paper process fits the close date.
- 13-18: real, but with gaps. Best case.
- 7-12: early or weak. Pipeline.
- 0-6: not qualified. Disqualify or go back to discovery.
Champion test
A friendly contact is not a champion. Ask:
- Have they given us information we couldn't get otherwise?
- Have they set up a meeting with someone more senior?
- Do they have a personal win if this happens?
- Would they say our name in a meeting we aren't in?
If the answer to all four isn't yes, the champion score is 1 at most.
Red flags
- The close date moved more than once.
- No meeting with the economic buyer, and the champion is "handling it".
- Pricing sent before the pain was quantified.
- The buyer hasn't done any work (no internal meeting, no data shared, no MAP).
- "We just need to get it through legal" with no legal contact.
- Single-threaded: only one contact in a deal over $50K.
- The close date is your quarter end, not their event.
Forecast category
- Commit: score 19+, EB engaged, paper process mapped to the close date, no open blockers.
- Best case: score 13+, path to close is clear but one or two gaps remain.
- Pipeline: real opportunity, not this period.
- Omit: not qualified.
When unsure, go one category lower. A sandbagged deal that closes is a pleasant surprise. A committed deal that slips costs credibility.
Output format
# Deal review: <Account>, <ACV>, close <date>
## MEDDPICC: <total>/24
| Element | Score | Evidence | Gap |
## Champion test: <pass / fail> - <why>
## Red flags
- ...
## Forecast: <Commit | Best case | Pipeline | Omit>
Reason: ...
## Next best actions (max 3, with owner and date)
1. ...
## Questions for the next call
- ...Example
Input: "$90K deal, close date end of month. Champion is the Support Ops manager, very excited. We demoed, sent pricing. VP Support was supposed to join but didn't. They're also talking to ConvoIQ."
- Metrics 1 (assumed improvement, no agreed number). EB 0 (VP never met). Decision criteria 1. Decision process 1. Paper process 0. Pain 2. Champion 1 (enthusiastic, no evidence of power). Competition 2. Total: 8/24.
- Red flags: pricing sent before the EB was engaged; single-threaded; close date is our month end.
- Forecast: Pipeline, not Commit.
- Next actions: (1) Ask the champion to set up 30 minutes with the VP to review the business case, by Friday. (2) Agree on the success metric with the VP. (3) Ask for the security questionnaire now to start the paper process.
Related skills
- discovery-call: fill the gaps this review finds.
- follow-up: build the mutual action plan.
- call-review: coach on the calls behind the deal.
- competitive-battlecard: when competition is the main risk.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.