agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/deal-qualification/SKILL.md

deal-qualification

Skill13 starsChanged 23 days agoMITView on GitHub

Use this skill when you need to qualify a B2B deal or check its health: \"qualify this opportunity\", \"MEDDICC this deal\", \"is this deal real\", \"score my opportunity\". Scores the deal on metrics, economic buyer, decision criteria, decision process, paper process, pain, champion and competition, separates what is confirmed from what is assumed, names the biggest gaps, and gives the questions and actions that close them before the forecast call.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this whenever a deal enters a forecast or moves stage.

    line 16
  2. Distinctive:

    Call notes, emails and the deal record.

    line 20
  3. Distinctive:

    Commit-stage deals usually need 2+ on every element and 3 on pain, champion and economic buyer.

    line 44
  4. Distinctive:

    MUST cap any element without evidence at 1.

    line 73
  5. Distinctive:

    MUST name one biggest gap with an owner and date.

    line 74
  6. Distinctive:

    NEVER recommend "commit" for a deal without an engaged economic buyer.

    line 75

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this whenever a deal enters a forecast or moves stage. It produces a scorecard that separates evidence from hope.

Inputs

  • Call notes, emails and the deal record.
  • Stage, amount and expected close date.
  • Who the rep has met and what each said.

The play

1. Score each element 0-3

ElementQuestion3 means
MetricsWhat measurable gain does the buyer expect?Number agreed with the buyer
Economic buyerWho signs and controls the budget?Met them; they confirmed the priority
Decision criteriaWhat will they judge options on?Written or stated criteria we influenced
Decision processWhat steps lead to a decision?Steps, people and dates mapped with the champion
Paper processWhat happens from "yes" to signature?Legal, security, procurement steps and timing known
Identify painWhat problem, how bad, why now?Pain with impact in their words and a reason for now
ChampionWho sells for us internally, with power?Tested: they took an action that cost them effort
CompetitionWhat else are they considering, including doing nothing?Named alternatives and why we win

0 unknown, 1 assumed, 2 partial evidence, 3 confirmed. Read references/meddicc-scorecard.md for scoring evidence examples and stage minimums.

2. Mark evidence

For each score, note the evidence and the source (call date, email). Anything without evidence is scored 1 at most.

3. Check stage minimums

Commit-stage deals usually need 2+ on every element and 3 on pain, champion and economic buyer. A deal below the minimum for its stage should move back a stage or out of the forecast.

4. Find the biggest gap

The weakest element on the critical path to signature, usually economic buyer, paper process or champion. One gap, one owner, one date.

5. Write the questions

Exact questions to ask next, phrased for the buyer, plus who should ask them.

Output format

Deal: <name> | <amount> | <stage> | close <date>
Scorecard: M x | EB x | DC x | DP x | PP x | IP x | C x | Comp x  (total /24)
Confirmed: <evidence list>   Assumed: <list>
Stage check: meets / below minimum for <stage>
Biggest gap: <element> - risk - action - owner - date
Next questions: <3-5>
Forecast call: commit / best case / pipeline / remove

What good looks like

  • Scores tie to evidence a manager can check.
  • The champion is tested, not just friendly.
  • The close date is backed by a paper process timeline.
  • The common mistake is scoring from the rep's optimism: "the economic buyer is the CFO" with no meeting is a 1, not a 3.

Rules

  • MUST cap any element without evidence at 1.
  • MUST name one biggest gap with an owner and date.
  • NEVER recommend "commit" for a deal without an engaged economic buyer.

Example prompts

  • "MEDDICC this deal from my notes and emails."
  • "Score my 6 commit deals and tell me which are really commits."
  • "What questions should I ask next week to qualify this opportunity?"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free