discovery-call-prep
Skill0 starsChanged 28 days agoMITView on GitHub
Prepares a one-page brief for a discovery or first sales call. Researches the company and attendees, forms pain hypotheses, and builds a call plan with opening, SPIN/GAP questions, likely objections and a clear next step to ask for. Use when the user says "prep me for my call with X", "discovery prep", "I have a meeting with [company]", "what should I ask [prospect]", or shares a meeting invite and wants to be ready.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- prosyo-ai/gtm-skilltheir own version, first seen Oct 25, 2026
- kesslernity/awesome-mistral-vibe-skillstheir own version, first seen Oct 20, 2026
- skills-agents-co/skills-and-agents-librarytheir own version, first seen Oct 15, 2026
- kesslernity/awesome-copilot-agent-skillstheir own version, first seen Oct 13, 2026
- bohorquezandrea/proposal-generatortheir own version, first seen Aug 26, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- kesslernity/awesome-copilot-agent-skills★ 16same name
- prosyo-ai/gtm-skill★ 13same name
- BenPrem/business-brain★ 1same name
- kesslernity/awesome-mistral-vibe-skills★ 1same name
- Nomanriaz786/claude-consulting-team★ 1same name
- skills-agents-co/skills-and-agents-library★ 1same name
- bohorquezandrea/proposal-generator★ 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 repository4 other files it gives its agents.
- call-to-crmSkill
- objection-handlerSkill
- sales-routerSkill
- signal-verified-outreachSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
If an ACCOUNT-<name>.md from signal-verified-outreach exists, start from it: the triggers there are already verified.
- Distinctive: line 76
Keep it scannable: the user reads it five minutes before the call.
- Very specific: line 78
After the call, call-to-crm can use this brief to check which hypotheses were confirmed and which MEDDICC gaps were closed.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Discovery Call Prep
Goal: walk into the call knowing what might be true, what you need to find out, and what next step you will ask for. Not a company encyclopedia.
Workflow
1. Collect the inputs
- Company, attendees (names, titles), meeting length, how the meeting came about (inbound, outbound, referral).
- What the user sells, and what a good outcome of this call looks like.
- Any prior notes, emails or CRM history the user can share.
- If an
ACCOUNT-<name>.mdfromsignal-verified-outreachexists, start from it: the triggers there are already verified.
2. Research, briefly and verifiably
- Company: what they do, size, recent news (last ~6 months) relevant to the offer. Use primary sources and cite them.
- Attendees: role, tenure, what they likely own, anything they have said publicly that relates.
- Mark anything uncertain as uncertain. Do not fill gaps with guesses.
3. Form 2 to 3 pain hypotheses
For each one:
Hypothesis: <what might be true>
Evidence: <verified fact + source>
Don't assume: <budget, owner, timing… whatever the evidence doesn't prove>
Question: "<how to test it>"
Strong signal if: <what answer would confirm it>These are things to test, not to state.
4. Build the call plan
Opening (first 2 minutes)
- Thank, confirm time, propose an agenda: "I'd like to understand your situation first, then share briefly how we work, and agree together whether a next step makes sense. OK?"
Questions: a control panel, not an essay
- 3 must-ask questions (tied to your hypotheses)
- 3 optional questions (if time allows)
- 1 disqualifying question (what answer would mean this is not a fit?)
- 1 next-step question
Draw them from:
- Situation: how things work today.
- Problem: where it breaks or slows down.
- Implication: what that costs (time, money, risk, growth).
- Need-payoff: what solving it would be worth.
- Decision: who else is involved, how they decide, timing, budget process.
Tie every question to a hypothesis. Avoid questions the research already answers.
Likely objections (2 to 3) with a short response each, using: acknowledge → clarify → reframe → advance.
Next step to ask for A specific, dated step: a second call with another stakeholder, a demo with the technical evaluator, a workshop. Never end on "I'll send some info".
5. Qualification checklist
Map what is known and unknown before the call (MEDDICC):
| Known | To find out | |
| Metrics | ||
| Economic buyer | ||
| Decision criteria | ||
| Decision process | ||
| Identify pain | ||
| Champion | ||
| Competition |
Output
One page, in this order: 30-second summary, attendees, hypotheses, call plan (opening, questions, objections, next step), MEDDICC table, sources. Keep it scannable: the user reads it five minutes before the call.
After the call, call-to-crm can use this brief to check which hypotheses were confirmed and which MEDDICC gaps were closed.
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.

