Discovery Call Prep

Grounded in The Mom Test and Transformed, this skill turns a hypothesis into a set of discovery-call questions you can actually use. Every question asks about something that already happened, never a hypothetical, and gets tagged with the product risk it tests: value, usability, feasibility, or business viability. It also flags any part of your hypothesis an interview simply can't answer, so you know what still needs a different kind of test. It ends with an ask that costs the person something real, since a real ask is the only signal that tells you whether they meant it.

First-party, by Skills and Agents Co

August 23, 2026

Install

Simple install — no setup required

1

Open the Claude desktop app and go to the Project you want this in

2

Go to Code, then Customize, then click Create a new skill and upload the skill file below

3

Say a trigger phrase to activate it

The skill file
Download
Or install with the CLInpx skills add skills-agents-co/skills-and-agents-library/discovery-call-prep

What this skill does

This is an overview of the skill from the site, not the skill's real instructions. The full SKILL.md Claude reads when this skill is active lives on GitHub at the source below.

Most discovery calls fail quietly. You ask someone whether they’d use a feature, they say “yeah, probably,” and you walk away with a false green light. This skill exists to stop that.

Give it a hypothesis and whatever you know about the person you’re about to talk to, and it builds you a question guide. Every question is written to ask about something that actually happened, not something the person imagines they’d do, because people are bad at predicting their own future behavior and polite about it to your face.

Each question also gets tagged with the risk it’s testing, drawn from Transformed’s four product risks: is this valuable, is it usable, can we build it, does it make business sense. That way you can look at your guide before the call and see if you’re only testing one risk while ignoring the other three.

The guide also tells you upfront what a conversation can’t settle. Some parts of a hypothesis need a prototype, a price test, or a pilot, not an interview, and it’s better to know that going in than to fool yourself with a good-sounding answer.

Finally, it ends every guide with a real ask, something that costs the person time, money, or a next step. If they won’t do it, you’ve learned something more useful than any answer they gave you.

View full SKILL.md on GitHub