Update to Great Question

{
  "description": "Use with the Great Question tools when writing, editing, or reviewing a screener. How we structure screener questions so they qualify the right participants, hide the qualifying intent, and filter out fraud.",
  "included_files": [],
  "name": "screener-creation",
  "skill_md_contents": "---\nname: screener-creation\ndescription: \"Use with the Great Question tools when writing, editing, or reviewing a screener. How we structure screener questions so they qualify the right participants, hide the qualifying intent, and filter out fraud.\"\n---\n\n# Screener Creation\n\nIf your Great Question workspace has its own skill for this, follow that instead.\n\nUse this whenever you create or edit a screener. A good screener qualifies the right people, screens out fraud, and stays short.\n\nPrefer templates? Check whether one of our vetted screener templates fits before authoring from scratch. Reuse beats reinvention, templates already encode our qualifying logic and anti-fraud checks.\n\n## Structure\n\n- Disqualify fast. Put the hardest qualification criteria first so unqualified respondents drop early.\n- Hide intent. Never phrase a question so the \"right\" answer is obvious. Mix in plausible distractor options.\n- One concept per question. Split compound questions.\n- Keep it under 8 questions. Longer screeners lower completion and raise cost.\n\n## Anti-fraud\n\n- Include at least one attention check (e.g. \"Select 'Somewhat agree' for this question\").\n- Include one open-text question early. Bots and click-farms reveal themselves in free text.\n- Avoid questions that let respondents guess the target demographic from the options alone.\n- Set qualifying answers explicitly. Don't rely on defaults.\n\n## Guardrails\n\n- Never ask for sensitive personal data (health, financial account numbers, government IDs) in a screener.\n- If the study needs sensitive eligibility criteria, flag it for a researcher rather than encoding it in the screener.\n"
}