screener-survey
Skill1 starsChanged 39 days agoMITView on GitHub
Write a recruiting screener that finds the right research participants without telling them the right answers. Use when someone needs to recruit for interviews or usability tests, write screener questions, set quotas, or filter a participant panel.
In this repository17 other files it gives its agents.
- accessibility-researchSkill
- ai-browser-walkthroughSkill
- analytics-insightsSkill
- card-sort-tree-testSkill
- competitive-analysisSkill
- diary-studySkill
- interview-guideSkill
- jobs-to-be-doneSkill
- journey-mapSkill
- research-planSkill
- research-readoutSkill
- stakeholder-interviewsSkill
- survey-designSkill
- synthetic-usersSkill
- usability-test-analysisSkill
- usability-test-planSkill
- user-personasSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Define who you need by behaviour,: not demographics: "compared car insurance quotes in the last six months", not "aged 25 to 40".
- Distinctive: line 26
Don't ask "Are you interested in X?" (everyone is).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Screener survey
A screener finds people who match the behaviour you're studying, while hiding which answers get them in.
Steps
- Define who you need by behaviour, not demographics: "compared car insurance quotes in the last six months", not "aged 25 to 40".
- Write disguised questions. Multiple choice where the qualifying answer sits among plausible others, so people can't guess their way in.
- Screen out professionals and repeat testers: people who work in UX, research, marketing or the industry being studied, and anyone who joined a study in the last few months.
- Add one open text question to check people can express themselves ("Tell us about the last time you..."), which also catches bots.
- Set quotas for the mix you need (devices, experience levels, assistive technology users) and over recruit by about 20% for no shows.
- Ask about accessibility needs so you can accommodate, not exclude.
- Keep it short: under ten questions. Collect only the personal data you need, and say how it's used.
Output
The screener with each question, its answer options, and which answers qualify, disqualify or need review, plus the quota table.
Don't
- Don't ask "Are you interested in X?" (everyone is). Don't reveal the product or the company if it biases who applies.
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.

