Screener builder
A Claude skill that turns a persona description into screener questions with qualifying logic, written so nobody can tell which answer gets them into the session.
Download the skill
Enter your details to download the skill file.
What it does
A screener is the short questionnaire deciding who gets into your study, sometimes called a recruitment screener or a qualifying survey. It manages one trade: precision against incidence. Every criterion you add improves the fit of the people you talk to and shrinks the pool you can draw from. Above that sits the rule everything else depends on, which is that the qualifying answer must never be guessable. Ask people whether they own a budget over a threshold, and they will own one.
This skill reads your persona description and converts each attribute into a question about behaviour that real people can answer honestly. A job title becomes what you actually did last quarter. Tool usage becomes which of these you opened this week, sitting in a list of options that all look equally plausible. Each question arrives with its own qualify and disqualify logic, and quotas come attached wherever you need a spread. An attention check sits where somebody clicking fast would trip over it.
What you get back
- Screener questions with answer options and the qualify or disqualify rule for each one.
- A map from persona attribute to the question testing it, including attributes nothing currently tests.
- Distractor options that make the qualifying answer hard to spot.
- Quota rules for the mix you want across your sessions.
- Screen-out copy that ends the survey without insulting anyone.
- A version you can paste into a Great Question screener or save as a screener template.
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
Download the skill
Fill in the short form to get the .skill file.
- 2
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.
- 3
Just ask
Ask in plain language. Claude picks up the skill on its own when the request matches.
Install in ChatGPT
- 1
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
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.
- 3
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
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
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.
- 3
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
Download and unzip the skill
The .skill file is a zip. Inside is SKILL.md, the instructions, plus any reference files the skill uses.
- 2
Make a Gem
In Gemini, go to Gems → New Gem. Paste SKILL.md into its instructions and add the reference files as knowledge.
- 3
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.
Build a screener for this persona: mid-market ops managers who own vendor renewals.
Rewrite question 3 so people can't tell which answer qualifies them.
This screener is disqualifying almost everyone. Which criterion is costing me the most?
What it won't do
It won't stop people lying to you. Hiding the qualifying answer raises the cost of guessing, and nothing inside a screener can verify that somebody holds the job they claim, so keep whatever verification your panel or your own customer data gives you. It also can't predict your incidence rate. It will flag criteria that look tight, and only a live screener tells you how tight they really are.
Questions
How do I stop professional participants getting through?
Hide the qualifying answer and ask about behaviour with a date attached, which is harder to fake on the spot than an identity claim. The skill also plants a consistency check: two questions that should agree, placed far apart, so contradictory answers surface in the responses. Protection at the panel level stays with wherever you recruit.
How long should a screener be?
Short enough that qualified people finish it. The skill starts from the criteria genuinely gating the study and pushes nice-to-know attributes into the session itself. If your criteria list demands a long screener, it will tell you which criteria are doing the least work for their length.
Can it build the screener inside Great Question for me?
This one writes the screener for you to paste in. If you want it created in the platform, the interview study builder is a Great Question skill that runs through our MCP and can set up the study along with its screener.
More skills
See all skillsScreener porter
Works on its ownA Claude skill that checks a recruitment screener before launch and helps you copy it into another study or tool without losing which answers qualify people.
RecruitingOctober 12, 2026
Stakeholder readout generator
Needs the Great Question MCPA Great Question skill that builds the readout from a finished study in your repo, with the real session highlights behind every finding so anyone can check the evidence themselves.
SynthesisAugust 27, 2026
Stakeholder readout
Works on its ownA Claude skill that turns findings sitting in your files into a readout ordered by the decisions it should inform, with the evidence for each headline attached underneath.
SynthesisJuly 23, 2026