Agent skill
discovery-call
Filed under Calls, demos and discovery.
From VijayMatt/go-to-market-agent-skills · 12 skills · 1 · pushed 2026-03-29
What it does when it runs
Read from the skill and the 3 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/VijayMatt/go-to-market-agent-skills.git /tmp/go-to-market-agent-skills git -C /tmp/go-to-market-agent-skills sparse-checkout set "discovery-call" mkdir -p ~/.claude/skills/discovery-call cp -R "/tmp/go-to-market-agent-skills/discovery-call/." ~/.claude/skills/discovery-call/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from VijayMatt/go-to-market-agent-skills/blob/c948db28e7a0147976cc91ad91479900a75f7904/discovery-call/SKILL.md, which is licensed MIT (repository). 3,012 words, 36 headings.
Discovery Call: MEDDIC/SPIN Hybrid Framework — Complete Methodology
The Core Principle
Discovery is not a demo with questions sprinkled in. It's a structured conversation designed to answer one question: should we both invest time in this deal? The best reps disqualify fast and qualify deeply. A 25-minute discovery call that ends in "this isn't a fit" is a win — you just saved 6 weeks of pipeline rot.
The hybrid MEDDIC + SPIN framework gives you two things:
- MEDDIC gives you the qualification rigor — who's the economic buyer, what's the decision process, what metrics matter
- SPIN gives you the conversational flow — situation, problem, implication, need-payoff — so your questions feel like a dialogue, not a deposition
Pre-Call Preparation (15-20 minutes)
This is non-negotiable. Walking into a discovery call unprepared is disrespectful to the prospect and guarantees surface-level conversation.
Research Checklist
Company-level (5 minutes):
- What does the company do? (In one sentence, from their website)
- How big are they? (Employees, revenue estimate, funding stage)
- What's their business model? (SaaS, services, marketplace, etc.)
- Recent news? (Funding, leadership changes, product launches, layoffs)
- Who are their competitors? (Helps you understand their market pressure)
- What technologies do they use? (BuiltWith, job postings, LinkedIn)
Person-level (5 minutes):
- What's their title and tenure? (New to role = mandate to change)
- What did they do before? (Previous company context)
- What have they posted on LinkedIn recently? (Topics they care about)
- Do they have mutual connections? (Referral opportunity)
- Have they engaged with your content? (Webinar, blog, download)
Deal-level (5 minutes):
- How did this meeting get booked? (Inbound, outbound, referral — affects dynamic)
- What did they say in the form / email / initial conversation?
- What's the buying signal that triggered outreach?
- Are there other stakeholders who should be on this call?
- What's your hypothesis for their top pain point?
Prepare 3 Hypotheses
Based on your research, form 3 hypotheses about their situation:
- Pain hypothesis: "I think their main pain is [X] because [evidence from research]"
- Impact hypothesis: "This pain probably costs them [Y] in [time/money/risk]"
- Trigger hypothesis: "They're looking now because [Z] happened"
Your goal in discovery is to validate or invalidate these hypotheses through conversation. This keeps you focused and prevents the call from wandering.
The MEDDIC + SPIN Hybrid Framework
MEDDIC Refresher
| Letter | Element | Core Question |
|---|---|---|
| M | Metrics | What measurable outcomes do they care about? |
| E | Economic Buyer | Who has budget authority and final sign-off? |
| D | Decision Criteria | What criteria will they use to evaluate solutions? |
| D | Decision Process | What are the steps between now and a signed contract? |
| I | Identify Pain | What specific problems are they trying to solve? |
| C | Champion | Who inside the organization will sell for you when you're not in the room? |
SPIN Refresher
| Letter | Question Type | Purpose |
|---|---|---|
| S | Situation | Understand their current state (use sparingly — you should know most of this from research) |
| P | Problem | Surface specific pain points |
| I | Implication | Expand the problem — what happens if they don't fix it? |
| N | Need-Payoff | Have them articulate the value of solving the problem |
The Hybrid: Conversation Flow
The trick is to use SPIN as the conversational engine and MEDDIC as the qualification checklist. You don't ask MEDDIC questions directly ("Who's the economic buyer?"). You use SPIN to uncover MEDDIC elements naturally.
The 30-Minute Discovery Call Structure
Phase 1: Frame the Call (2-3 minutes)
Goal: Set expectations, build rapport, establish mutual agenda.
Script framework:
"Thanks for making time, [name]. Here's what I was thinking for our conversation — I did some research on [company] and I have a few hypotheses about what might be going on, but I'd rather hear it from you. I'll ask some questions about your current setup and the challenges you're facing, and then we can figure out together if there's a reason to keep talking. Does that work? Is there anything specific you wanted to cover?"
Why this works:
- Shows you did your homework
- Frames it as a two-way evaluation (not a sales pitch)
- Gets their buy-in on the agenda
- Lets them surface their top priority immediately
Red flag: If they say "just walk me through your product," redirect: "Happy to — but I want to make sure I show you the right things. Can I ask a few questions first so I don't waste your time on features that aren't relevant?"
Phase 2: Situation (3-4 minutes)
Goal: Confirm your research and understand their current state. Keep this SHORT. Every situation question you ask that you could have answered with research makes you look unprepared.
Good situation questions (confirm, don't discover):
- "I saw you're using [tool] for [function] — is that still the case?"
- "It looks like your team is about [X] people — is that right?"
- "I noticed you recently [hired/raised/launched]. How has that changed things?"
Bad situation questions (do your homework):
- "So, what does your company do?" (Never ask this)
- "How big is your team?" (Look it up)
- "What tools do you use?" (Check BuiltWith/LinkedIn first)
MEDDIC elements captured: Metrics (current state baseline), Decision Criteria (how they evaluate tools today)
Phase 3: Problem (8-10 minutes)
Goal: Uncover 2-3 specific, concrete pain points. This is the heart of the call.
Question sequencing:
Start broad, then drill down:
- Opening problem question: "What's the biggest challenge your team faces with [area your product addresses]?"
- Follow-up for specificity: "Can you give me an example of when that happened recently?"
- Quantification: "How often does that happen? What does it cost you when it does?"
- Stakeholder impact: "Who else on your team feels this pain?"
The "tell me more" technique: When they mention a pain point, resist the urge to jump to your solution. Instead, say "Tell me more about that" or "Walk me through what happens when [pain event] occurs." This gets you deeper, more specific information and makes the prospect feel heard.
MEDDIC elements captured: Identify Pain (primary and secondary pain points), Champion (the person who feels the pain most acutely)
Phase 4: Implication (5-7 minutes)
Goal: Expand the problem. Help them see the full cost of inaction. This is where good reps separate from average reps.
Implication questions:
- "What happens if you don't fix this in the next 6 months?"
- "How does this affect [other department/metric/goal]?"
- "What did this cost you last quarter — in time, money, or missed targets?"
- "When [pain event] happens, what's the ripple effect?"
- "How does this impact your ability to [strategic goal they mentioned]?"
The multiplication technique: Take their specific example and multiply it: "You said this happens about 3 times a month and takes 4 hours each time. So that's 144 hours a year — almost a full headcount — spent on [painful task]. Is that roughly right?"
When you let the prospect do the math, they sell themselves on the urgency.
MEDDIC elements captured: Metrics (quantified impact), Economic Buyer (who cares about these numbers)
Phase 5: Need-Payoff (3-4 minutes)
Goal: Have THEM articulate what the solution looks like. Do not pitch your product here. Ask what good looks like.
Need-payoff questions:
- "If you could wave a magic wand, what would this process look like?"
- "What would it mean for your team if [pain] went away?"
- "If you solved this, what metric would you expect to improve?"
- "What would you do with those 144 hours back?"
Why this works: When the prospect describes the ideal state, they're writing your proposal for you. They've just told you exactly what to demo, what to put in the ROI analysis, and what success looks like.
MEDDIC elements captured: Metrics (target state), Decision Criteria (what "good" looks like to them)
Phase 6: Process and Next Steps (5-7 minutes)
Goal: Understand the buying process and establish next steps. This is where most reps drop the ball.
Process questions (MEDDIC: Decision Process + Economic Buyer):
- "If we both decide this is a fit, what does your evaluation process look like?"
- "Who else would need to be involved in this decision?"
- "Have you bought a tool like this before? What was that process like?"
- "Is there a timeline driving this? What's creating urgency?"
- "Is there budget allocated for this, or would we need to build a business case?"
The direct approach (for strong rapport):
"I want to be upfront — I'm trying to understand if this is a real project with a real timeline and real budget, or if this is more exploratory. Either is fine, but it helps me know how to prioritize and what to show you. Where would you put this?"
Establishing next steps: Never end a call without a specific next step. "I'll follow up" is not a next step.
Good next steps:
- "Can we schedule a 45-minute demo for Thursday with [other stakeholder] on the call?"
- "I'll send you a 1-page summary of what we discussed and a case study from [similar company]. Can we regroup on Friday to discuss?"
- "It sounds like you need to socialize this internally first. Can I put 15 minutes on the calendar for next Tuesday to see where things stand?"
MEDDIC elements captured: Economic Buyer, Decision Process, Champion (who will advocate internally)
Red Flags vs. Green Flags
Green Flags (deal is real)
| Signal | What it means |
|---|---|
| They share specific numbers | They trust you and they've measured the pain |
| They mention other stakeholders by name | There's an active buying committee |
| They ask about implementation timeline | They're thinking about operationalizing |
| They share competitive context | "We're also looking at [competitor]" = active evaluation |
| They offer to introduce you to their boss | You have a champion |
| They describe a triggering event | There's urgency, not just curiosity |
| They ask tough questions about your product | They're seriously evaluating |
| They push for a faster timeline | Internal pressure to solve this |
Red Flags (proceed with caution)
| Signal | What it means | How to probe |
|---|---|---|
| "We're just looking" | No urgency, no timeline | "What would need to happen to move this from exploratory to a real project?" |
| Won't share budget range | Either no budget or not the decision-maker | "I'm not asking for a PO number — just trying to make sure we're in the same ballpark" |
| Only one person on every call | No buying committee, likely a lone evaluator | "Who else would weigh in on this decision?" |
| "Just send me some information" | Trying to end the conversation | "Happy to — what specifically would be most useful? I want to send you the right thing, not a generic deck" |
| Can't articulate the pain | They took the meeting but don't have a problem | "Help me understand what prompted you to take this meeting" |
| Keeps rescheduling | Low priority | After 2 reschedules, ask directly: "I want to respect your time — should we revisit this when the timing is better?" |
| Won't commit to next steps | No momentum | "It sounds like the timing might not be right. Would it be more helpful to reconnect in Q3?" |
| "We're building this in-house" | Build vs. buy competition | "That's a valid approach. What's the timeline and team size for the build? I can share what we've seen other teams struggle with" |
Real-Time Note-Taking Framework
During the call, capture notes in this structure. This becomes your CRM update and your deal strategy.
## Discovery Notes: [Company] | [Date]
### Pain Points Identified
1. [Specific pain] — Frequency: [X/month] — Impact: [$Y or Z hours]
2. [Specific pain] — Frequency: [...] — Impact: [...]
3. [Specific pain] — Frequency: [...] — Impact: [...]
### MEDDIC Scorecard
- Metrics: [What they measure, target numbers]
- Economic Buyer: [Name, title — or unknown]
- Decision Criteria: [What matters most to them]
- Decision Process: [Steps, timeline, stakeholders]
- Identified Pain: [Top 1-2 pains in their words]
- Champion: [Name, title, enthusiasm level]
### Key Quotes (verbatim)
- "[Exact quote about pain]"
- "[Exact quote about impact]"
- "[Exact quote about desired outcome]"
### Competitive Context
- Currently using: [tool/process]
- Also evaluating: [competitors]
- Why looking to switch: [reason]
### Next Steps
- [ ] [Specific action] by [date]
- [ ] [Specific action] by [date]
### Deal Score: [X/10] — [Worth pursuing / Monitor / Disqualify]
Capture verbatim quotes whenever possible. These are gold for proposals, ROI calculations, and follow-up emails. "You mentioned that [exact quote]" is 10x more powerful than "you said something about [vague paraphrase]."
Post-Call Scoring
After every discovery call, score the deal on a 1-10 scale across these dimensions:
| Dimension | Weight | Score Criteria |
|---|---|---|
| Pain clarity | 25% | 1 = vague discomfort, 10 = specific, quantified, urgent pain |
| Economic buyer identified | 20% | 1 = unknown, 10 = identified by name, you know their priorities |
| Decision process clarity | 15% | 1 = "I don't know," 10 = clear steps, timeline, criteria |
| Champion strength | 15% | 1 = no champion, 10 = enthusiastic, influential, will sell for you |
| Budget indication | 15% | 1 = no budget discussion, 10 = budget allocated, ballpark confirmed |
| Competitive position | 10% | 1 = you're behind, 10 = you're the front-runner |
Scoring thresholds:
- 8-10: Strong qualify. Advance to demo/proposal. Fast-track this deal.
- 6-7: Conditional qualify. Advance, but identify what's missing and fill the gap.
- 4-5: Weak qualify. One more conversation to fill gaps, then decide.
- 1-3: Disqualify. Thank them, put them in nurture, move on.
Handling Common Discovery Scenarios
Scenario 1: "Just send me some information"
What's happening: They want to end the call without committing to anything.
Response: "Happy to send you something — but I want to make sure it's relevant. Can I ask two quick questions so I send the right materials? [Ask one problem question and one process question.] Based on what you've told me, I'll send [specific thing] and we can schedule 15 minutes next week to discuss whether it makes sense to continue."
Goal: Convert a brush-off into a committed next step.
Scenario 2: Prospect goes silent mid-call
What's happening: They're distracted, not engaged, or not feeling the relevance.
Response: "I want to make sure I'm asking the right questions here. Is this the challenge you were hoping to discuss, or is there something else that's more pressing?"
Goal: Re-engage by giving them control of the conversation direction.
Scenario 3: "What's the price?"
What's happening: They want to skip discovery and evaluate on price alone.
Response: "I can give you a ballpark — we typically range from [low] to [high] depending on [key variable]. But the number that matters more is [ROI metric]. Can I ask a couple questions so I can estimate what the impact would look like for your team? That way you can evaluate the price against the return."
Goal: Reframe the conversation from cost to value without refusing to answer.
Scenario 4: "We're happy with our current solution"
What's happening: They took the meeting but don't see a reason to change (yet).
Response: "That's great — I'd rather talk to someone who has a working process than someone in crisis mode. Out of curiosity, if you could change one thing about how [process] works today, what would it be?"
Goal: Find the crack in satisfaction. Everyone has one thing they'd change.
Scenario 5: "Can you just do a quick demo?"
What's happening: They want to see the product before sharing information.
Response: "Absolutely, I want to show you the product. But our demo is customizable, and I want to show you the parts that are actually relevant to you — not a generic walk-through. Can I ask 3-4 questions first? Then I'll show you exactly how we'd handle your specific situation."
Goal: Trade questions for a better demo experience.
Anti-Patterns
1. The interrogation. Firing questions without reacting to answers. Discovery is a conversation, not a survey. Respond to what they say before asking the next question.
2. Premature solutioning. They mention a pain and you immediately jump to "we solve that!" Stay in discovery. Let the pain expand before you offer the cure.
3. Feature-checking. "Do you need X? Do you need Y? Do you need Z?" This is not discovery. This is a feature checklist that tells you nothing about pain or value.
4. Happy ears. Hearing what you want to hear. They say "that's interesting" and you log it as a green flag. "Interesting" means nothing. Look for commitment signals: willingness to share data, introduce stakeholders, schedule follow-ups.
5. Skipping the "why now." Understanding what they need is not enough. You must understand why they're looking NOW. Without a trigger, there's no urgency and the deal will stall.
6. Single-threaded discovery. Only talking to one person. A deal with one contact is not qualified. You need at minimum a champion and an economic buyer identified.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- discovery-call-prep by composio-community · 2
- discovery-call-prep by devangk003 · 0
- community-discovery by shawnpang · 308
- discovery by louisblythe · 136
- niche-signal-discovery by getaero-io · 54
- call-analysis by Salesably · 48
- cold-call-scripts by Salesably · 48
- analyse-call by himanshusaleria · 16
Need help setting it up?
This page tells you what discovery-call does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.