── SKILL
discovery-framework✓ APPROVED

Turn a discovery call into a qualification scorecard.

Runs your call against MEDDPICC or your own framework, captures the deal, and names the gaps you still have to fill.

Inside: The field-by-field scorecard, the pain quantifier, and the champion test.

01 / HOW TO USE

Install it in one line, or paste it in.

1
In Claude Code (one command)
Copy the install line, paste it into your terminal, and restart Claude Code. The skill installs itself to ~/.claude/skills/ and runs automatically when it is relevant.
2
In Claude, ChatGPT, or a Project (no terminal)
Open the file, then upload it to your chat or paste its contents in. A skill is just a markdown file of instructions, so any capable AI can follow it.
New to skills? A skill is a plain-text file that teaches your AI a workflow. Point any capable assistant at it and it follows the steps, on your data.
02 / MAKE IT YOURS

Connect your context. Set it to your motion.

CONNECT YOUR CONTEXT · AND WHY IT HELPS
a meeting or transcription tool

it reads the call directly, pulls the buyer's own quotes, and stops you from scoring pain you only imagined.

Sharper connected to a CRM

it writes each field back to the opportunity and checks the qualification against the stage the deal claims.

SET IT TO YOUR MOTION

This was built for a B2B SaaS org running MEDDPICC. Set these to your stack:

Run any framework you like. The skill scores "what did the buyer actually tell you," so point it at your fields, not anyone else's.

Set thisWhat it isDefault / Example
FRAMEWORKyour qualification methodologyMEDDPICCMEDDICBANTyour own
MEETING sourcewhere calls are recordedyour meeting or transcription tool
STAGE fieldthe opportunity stageOpportunity.StageName
PAIN fieldswhere impact and metrics liveyour custom qualification fields
CHAMPION testwhat proves a champion is realacts when you are not in the room
QUANTIFY unithow you size painhoursdollarsheadcountchurn
03 / THE FULL SKILL

Everything the skill does, in full.

── WHAT THIS DOES

Takes what you learned on a discovery call and lays it out on a qualification framework, one field at a time. It captures the problem in the buyer's words, the impact and quantified pain, how they actually buy, who signs, and who is fighting for you inside. Then it does the part reps skip: it names what you still do not know and what to ask next.

── THE METHOD
  1. 1
    Score every field, name every gap

    Each framework field gets one of three states: EARNED (the buyer said it, and you can quote it), ASSUMED (you inferred it, not confirmed), or MISSING. Assumed and missing are the deal risk. The output leads with them, not with the fields you already have.

  2. 2
    Problem before solution

    Capture the problem in the buyer's language first, before any product talk. If you cannot write the problem as a sentence the buyer would agree with, you do not have discovery, you have a pitch.

  3. 3
    Quantify the pain

    Pain without a number is a nice-to-have. Push for the metric: hours lost, dollars leaking, deals slipping, the cost of the status quo. If the number is not there yet, mark it MISSING and make it the next call's job. An illustrative example: "roughly 6 hours a week per rep on manual list building" is a quantified pain, "it is a pain" is not.

  4. 4
    Decision process and economic buyer

    Map how they buy, not just who likes you. Who signs, what the steps are, what has killed a deal like this before, whether you have met the person who controls the budget. Liking you is not access.

  5. 5
    Champion versus contact

    A contact takes your call. A champion sells for you when you are not there and has something to gain if this lands. Test it: have they given you something that cost them anything, an intro, a proof point, an internal date. If not, mark champion ASSUMED.

── QUALITY GATES
  • No field scored EARNED without a quote or a specific fact behind it.
  • Quantified pain is a number with a unit, or it is MISSING, never "significant."
  • Champion is not marked real until they have taken one action for you unprompted.
  • The gap list is ranked by deal impact, not by framework order.
── OUTPUT (EXAMPLE)
EXAMPLE OUTPUT
DISCOVERY SCORECARD · illustrative deal
Field                   State     What we have
Metrics (pain)          EARNED    ~6 hrs/wk/rep on manual prospecting
Economic Buyer          ASSUMED   VP Sales named, not yet met
Decision Criteria       EARNED    Must cut ramp time, integrate with CRM
Decision Process        MISSING   No steps, no timeline captured
Identified Pain         EARNED    Reps miss quota in first two quarters
Champion                ASSUMED   Enthusiastic, no action taken yet
Competition             MISSING   Not asked

Top gaps to close next call:
  1. Decision process. Get the actual steps and dates to signature.
  2. Meet the economic buyer. A named VP you have not met is not access.
  3. Test the champion. Ask for one internal intro and see what happens.
── EXAMPLE CHAT
EXAMPLE CHAT
You
I just got off a discovery call, here are my notes, tell me what I'm missing.
CLAUDE
Scored the call against MEDDPICC. Field State What we have Metrics (pain) EARNED ~6 hrs/wk/rep on manual prospecting Economic Buyer ASSUMED VP Sales named, not yet met Decision Process MISSING No steps, no timeline captured Champion ASSUMED Enthusiastic, no action taken yet The catch: you have got real pain and real decision criteria, but two fields you would probably call fine are actually ASSUMED, not earned, meaning nobody has confirmed them yet, and Champion has not taken a single unprompted action.
You
What's the one question that would move this the most next call?
CLAUDE
Get the actual decision process, steps and dates to signature. That is the only MISSING field, and it is the one that determines whether Commit means anything. One sharpener: connect a meeting tool so the scorecard pulls your buyer's exact words next time instead of relying on your notes to be complete.
04 / GO FURTHER

Where an operator takes this next.

The read is step one. Here is where an operator takes it once the manual version proves out.

Earn the field or flag it. Do that at scale and coaching gets specific instead of generic.

01
Score every call automatically

Connect Gong or another transcript tool so this runs the moment a discovery call ends, no copy-paste required.

02
Write straight back to the deal

Connect Salesforce so EARNED fields populate the opportunity record automatically, and gaps show up in the pipeline report as real risk.

03
Catch the pattern across reps

Schedule a Claude task weekly to roll up gap types across the team, so a manager sees "champion is ASSUMED on 40% of deals" instead of one call at a time.

05 / PART OF A BIGGER PLAY

One skill is the on-ramp.

── GET NEW SKILLS IN YOUR INBOX

One operator-built skill a week. Free.