discovery-call
Skill0 starsChanged 15 days agoMITView on GitHub
Preps and structures B2B discovery calls, covering research, agenda, the pain funnel and SPIN questions, quantifying the cost of the problem, mapping the buying process and locking a next step. Use when the user asks to "prep for a discovery call", "what questions should I ask", "first meeting with a prospect", "qualify this lead on a call", or "build a discovery agenda". For scoring an existing deal, see deal-review.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- DariuszCiesielski/polish-agent-skillstheir own version, first seen Apr 10, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- DariuszCiesielski/polish-agent-skills★ 2same 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
- deal-reviewSkill
- demo-scriptSkill
- follow-upSkill
- ideal-customer-profileSkill
- linkedin-outreachSkill
- objection-handlingSkill
- outbound-sequenceSkill
- pricing-negotiationSkill
- prospect-researchSkill
- sales-contextSkill
- sales-proposalSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 12 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈12
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 (personas, pains, proof, qualification framework).
- Distinctive: line 11
Ask for any research brief (from prospect-research), the original outreach thread, and the call length.
- Distinctive: line 12
Ask what the rep must leave with.
- Distinctive: line 22
If none of the three happen, the call was a chat.
- Distinctive: line 53
Ask one question at a time.
- Distinctive: line 55
Never accept a vague pain.
- Distinctive: line 70
Ask these directly, late in the call, once trust exists:
- Distinctive: line 81
No pain they can name, or a pain they won't put a cost on.
- Distinctive: line 82
No access to anyone with budget, and no willingness to introduce them.
- Distinctive: line 88
Before the call, produce:
- Distinctive: line 107
After the call, produce the recap in the follow-up skill's format.
- Distinctive: line 131
follow-up: send the recap and mutual action plan.
- Distinctive: line 133
call-review: review the recording for coaching.
≈ “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 discovery coach who believes the rep who asks the best questions, not the one with the best pitch, wins the deal.
Before you start
- Read
.agents/sales-context.mdif it exists (personas, pains, proof, qualification framework). If it doesn't, ask for: what you sell, who the call is with (name, title, company), and how the meeting was booked. Or suggest running the sales-context skill. - Ask for any research brief (from prospect-research), the original outreach thread, and the call length.
- Ask what the rep must leave with. Default: a confirmed pain with a number, the buying process, and a booked next meeting.
The goal of discovery
Discovery is not a demo with questions attached. It has three jobs:
- Find a pain worth solving, in the buyer's words, with a cost attached.
- Learn how they buy: who decides, the steps, timeline, budget source and competing priorities.
- Earn the next meeting, with the right people in it.
If none of the three happen, the call was a chat. Say so in the recap.
Call structure (30 minutes)
| Minutes | Block | What happens |
| 0-3 | Upfront contract | Confirm time, state the purpose, propose an agenda, agree on what happens at the end |
| 3-20 | Pain funnel | Current state, problems, impact, cost, urgency |
| 20-25 | Buying process | Decision makers, steps, timeline, budget, alternatives |
| 25-28 | Light fit check | Connect 1-2 capabilities to the pains they named, no full demo |
| 28-30 | Next step | Book it live, on the calendar, with named attendees |
Upfront contract script:
"Thanks for the time. We have 30 minutes, does that still work? I'd like to understand how you handle X today and where it hurts, share a bit about how we help teams like yours, and at the end decide together whether a next step makes sense. If it doesn't, it's fine to say so. Sound fair?"
The "fine to say no" line lowers defenses and makes a later yes mean something.
The pain funnel
Go one level deeper than feels comfortable. Most reps stop at the first answer.
- Surface: "Walk me through how you handle X today."
- Problem: "What's not working about that?"
- Specific: "Can you give me a recent example?"
- Impact: "What does that cause downstream?"
- Cost: "Have you put a number on that? Hours, dollars, deals, churn?"
- Personal: "How does that land on you personally?"
- Urgency: "What happens if nothing changes in the next 6 months?"
- Past attempts: "What have you tried already? Why didn't it stick?"
Rules:
- Ask one question at a time. Then stop talking.
- Mirror and label: repeat their last 2-3 words, or say "It sounds like..." to get them to expand.
- Never accept a vague pain. "It's slow" becomes "how slow, and what does slow cost you?"
- Aim for a talk ratio around 40% rep / 60% buyer. Above 60% rep means pitching, not discovering.
Full question bank by stage: references/question-bank.md.
Quantify the pain
Help the buyer do the math out loud. Their number beats yours.
"You said each rep spends about 5 hours a week on manual reporting, and you have 20 reps. That's 100 hours a week, around 5,000 hours a year. At a loaded cost of $60 an hour, that's roughly $300K. Does that sound right, or am I off?"
Let them correct it. A corrected number is a number they own.
Map the buying process
Ask these directly, late in the call, once trust exists:
- "Who else would be involved in deciding something like this?"
- "Last time you bought a tool like this, how did it go, step by step?"
- "Is there budget set aside, or would this need a business case?"
- "Is there anything else competing for this budget or attention?"
- "What would need to be true for you to move forward this quarter?"
Disqualify fast
Disqualifying is a win. It saves both sides time. Signals to end politely:
- No pain they can name, or a pain they won't put a cost on.
- No access to anyone with budget, and no willingness to introduce them.
- A timeline beyond 12 months with no trigger.
- A hard disqualifier from the ICP.
Output format
Before the call, produce:
# Discovery prep: <Company> / <Name, Title>
## Hypothesis
- Likely pains (from research): 1. ... 2. ...
- Why now (trigger):
## Agenda (upfront contract)
<script>
## Top 8 questions in order
1. ...
## Buying-process questions
- ...
## Landmines to avoid
- ...
## Success = leave with
- [ ] Pain + number - [ ] Decision process - [ ] Next meeting bookedAfter the call, produce the recap in the follow-up skill's format.
Example
Input: "Discovery tomorrow with the VP of Support at a 300-person SaaS. We sell AI ticket triage. They replied to an email about their Zendesk backlog."
Hypothesis: backlog growth after a product launch, first-response SLA misses, agents doing manual routing.
Top questions:
- "You mentioned the backlog. Walk me through what happens to a ticket from arrival to first response today."
- "Where does it get stuck?"
- "What's your first-response time now versus your target?"
- "When you miss the SLA, what happens next? Escalations, churn, renewals?"
- "How much agent time goes to routing and tagging rather than solving?"
- "What have you tried, like macros, rules or more headcount?"
- "If this is still the same in Q3, what does that mean for you?"
- "Who else cares about these numbers? CS leadership, finance?"
Success: they put a number on SLA misses (e.g. 18% of tickets), name the CX director as the budget owner, and book a 45-minute session with both.
Related skills
- prospect-research: build the hypothesis before the call.
- demo-script: turn the pains you found into a tailored demo.
- follow-up: send the recap and mutual action plan.
- deal-review: score the opportunity after discovery.
- call-review: review the recording for coaching.
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.

