Interview study builder
A Great Question skill that takes a description of the study you want and builds it in your account, where it waits for your review before it goes anywhere.
Download the skill
Enter your details to download the skill file.
What it does
A moderated interview study is a run of one-on-one sessions with real people, scheduled against a single research question and recorded so the team can go back to it. Researchers also call these depth interviews or IDIs, and discovery interviews when the work is generative. The conversation is the part everyone remembers. The setup is the part that eats the week: writing the objective down, drafting a screener, deciding who qualifies, choosing session length, then getting all of it into a study that can actually be sent.
This skill does that setup inside Great Question. You describe the study the way you would describe it to a colleague, and one call creates it: the title, the research goal participants see, the session length, the meeting provider, whether that is Zoom, Google Meet, Microsoft Teams, Webex, in person or a URL you paste in, and the availability behind it, from weekly hours and a booking window through to buffers either side of a call and the minimum notice you need. Nothing goes out. You open the study, read what was built, and change whatever you want before it moves. It runs from Claude, Cursor or ChatGPT once the Great Question MCP is connected, so the study gets built in the same window where you worked out the question.
What you get back
- An interview study created in your Great Question account, waiting for your review.
- The research goal and session length written in, with the meeting provider set to Zoom, Google Meet, Microsoft Teams, Webex, in person or a URL you supply.
- Availability, booking limits per day and per week, buffers, notice periods and a cap on how many people can take part, all set from what you described.
- A screener written from scratch, or an existing screener template copied onto the study, which replaces every question already there.
- Screener questions in the shape each one needs: single and multiple choice carrying qualifying and disqualifying answers, yes/no, number ranges, dates, location and matrix, with skip logic that branches to another question or ends the screener early.
- An incentive set up the way you actually pay people, manual, Tremendous, coupon or product, with amount, currency and redemption instructions, plus a consent form chosen from your account's list.
Install it in Claude, ChatGPT, Copilot or Gemini
The same skill file works in all four. Pick your tool for the steps.
Install in Claude
- 1
Connect the Great Question MCP to Claude
These skills act inside your Great Question account, so the MCP has to be connected first. The MCP guide has the setup for each tool.
- 2
Download the skill
Fill in the short form to get the .skill file.
- 3
Add it to Claude
In the Claude app go to Settings → Capabilities → Skills and upload the file. In Claude Code, run the npx command shown after the form, or drop the folder into your project's skills folder.
- 4
Just ask
Ask in plain language. Claude picks up the skill on its own when the request matches.
Install in ChatGPT
- 1
Connect the Great Question MCP to ChatGPT
These skills act inside your Great Question account, so the MCP has to be connected first. The MCP guide has the setup for each tool.
- 2
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 3
Make a Custom GPT or a Project
Create a Custom GPT (Explore GPTs → Create → Configure) or a Project. Paste SKILL.md into its instructions and upload the reference files as knowledge.
- 4
Just ask
Open that GPT or Project and ask in plain language. It follows the skill's method every time.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
Install in Microsoft Copilot
- 1
Connect the Great Question MCP to Microsoft Copilot
These skills act inside your Great Question account, so the MCP has to be connected first. The MCP guide has the setup for each tool.
- 2
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 3
Build a Copilot agent
In Microsoft 365 Copilot, open Agent Builder and create an agent. Paste SKILL.md into its instructions and add the reference files as knowledge.
- 4
Just ask
Open the agent and ask in plain language. Share it with your team so everyone runs the same method.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
Install in Gemini
- 1
Connect the Great Question MCP to Gemini
These skills act inside your Great Question account, so the MCP has to be connected first. The MCP guide has the setup for each tool.
- 2
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 3
Make a Gem
In Gemini, go to Gems → New Gem. Paste SKILL.md into its instructions and add the reference files as knowledge.
- 4
Just ask
Open the Gem and ask in plain language. It follows the skill's method every time.
If the instructions box won't take the whole of SKILL.md, upload SKILL.md as a knowledge file instead and write one line of instructions: follow SKILL.md for every request.
How to use it
Once it's installed, ask in plain language. Your AI follows the skill's method when the request matches.
Set up a 45 minute interview study on why finance teams abandon the reconciliation flow.
Build an interview study for eight customers who upgraded in the last quarter, and draft the screener with it.
Same shape as last month's onboarding round, but for enterprise admins.
What it won't do
It won't send the study or put anyone in a session. There is no duplicate operation either, so an earlier round gets rebuilt from your description rather than copied. Moderators are added as a separate step once the study exists. And a one line description produces a one line study: the objective and screener are only ever as specific as what you told it.
Questions
Does it send anything to my customers?
No. The study is built and then left alone for you to review. Recruiting and messaging are separate steps, handled by separate skills.
How is this different from the discussion guide builder?
The discussion guide builder is a Claude skill that writes a guide from files, with no account involved. This one works inside Great Question and produces a study you can run, so nothing has to be re-keyed afterwards.
Can it use a study I already ran as a starting point?
There is no duplicate operation, so nothing gets copied across. Describe the earlier round and it builds a study of that shape from your description, which lets you change the audience or the session length as you go. The earlier study stays exactly where it is.
More skills
See all skillsJTBD analyzer
Works on its ownA Claude skill that codes interview transcripts against the Jobs to be Done framework, returning the four forces and the moment someone actually switched, with the quote behind each one.
AnalysisJuly 9, 2026
JTBD interview guide builder
Works on its ownA Claude skill that writes a full JTBD moderation guide around the Moesta timeline interview, including the probes that get someone back to what actually happened.
Study designJuly 2, 2026
Moderator scorecard
Works on its ownA Claude skill that shows you, from your own interview transcript, how much you talked, interrupted or led the participant, so you can get better at moderating.
Research opsOctober 12, 2026