How do I install the Research Questionnaire skill?

Run npx skillmds@latest add frankglendon/research-questionnaire in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Research Questionnaire safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Research Questionnaire?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Research Questionnaire free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Research Questionnaire?

frankglendon (@frankglendon) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Research Questionnaire by frankglendon

Name: Research Questionnaire
Author: frankglendon

Research Questionnaire

Design a structured research questionnaire, analysis mapping and programming specification with survey logic checks. Use for screening, scales, multi-choice, matrices, ranking and questionnaire revisions.

frankglendon cc2549b 6 files · 11.3 KB Updated Sep 17, 2026

File contents

Draft a structured questionnaire

Map business decisions to metrics and questions before drafting. Identify the population, screening criteria, sampling assumptions, languages, timing and pilot plan. Learn structure from authorized local references without inheriting client content or fixed project parameters.

Read schema v2. For reference-level deliverables, use the professional benchmark to find and close substantive gaps. Review wording for one concept per question, an explicit recall period, balanced labels and non-overlapping categories. Preserve existing scale definitions when comparability matters.
Keep unprompted awareness ahead of prompted lists. Distinguish not-asked, unknown, inapplicable and substantive zero. Special codes are project-defined; Other is not automatically exclusive. Randomization changes display order, never stored codes.
Run python scripts/run.py survey-check --spec SPEC. Add synthetic routing cases and run survey-simulate --spec SPEC --cases CASES. The simulator covers explicit forward routes and display conditions, not arbitrary prose or a live survey platform.
Review content, programming and analysis; bind the current specification hash. survey-run --spec SPEC --output OUTPUT provides a baseline export; use the host's Office workflow for professional master and appendix layout. Missing routing branch coverage or stale reviews block export.
Use research-codebook to generate the matching Datamap. Check variable names, multi-response storage, matrix dimensions and missing rules; then inspect Office validity and layout.

Do not invent incidence rates or quotas. Review marginal quota totals separately per dimension. Calibrate timing and quality rules through a pilot; do not assume one cutoff fits every study. Business review and fieldwork piloting remain required beyond the compiler checks.

The original small questionnaire --plan PLAN workflow remains supported through its legacy protocol. Prefer v2 for new studies.

This skill requires the shared Python package installed from this repository. It does not run a web server or grant authority to publish or message anyone.

---name: research-questionnairedescription: Design a structured research questionnaire, analysis mapping and programming specification with survey logic checks. Use for screening, scales, multi-choice, matrices, ranking and questionnaire revisions.---# Draft a structured questionnaireMap business decisions to metrics and questions before drafting. Identify the population, screening criteria, sampling assumptions, languages, timing and pilot plan. Learn structure from authorized local references without inheriting client content or fixed project parameters.1. Read [schema v2](references/survey-v2.md). For reference-level deliverables, use the [professional benchmark](references/benchmark.md) to find and close substantive gaps. Review wording for one concept per question, an explicit recall period, balanced labels and non-overlapping categories. Preserve existing scale definitions when comparability matters.2. Keep unprompted awareness ahead of prompted lists. Distinguish not-asked, unknown, inapplicable and substantive zero. Special codes are project-defined; Other is not automatically exclusive. Randomization changes display order, never stored codes.3. Run `python scripts/run.py survey-check --spec SPEC`. Add synthetic routing cases and run `survey-simulate --spec SPEC --cases CASES`. The simulator covers explicit forward routes and display conditions, not arbitrary prose or a live survey platform.4. Review content, programming and analysis; bind the current specification hash. `survey-run --spec SPEC --output OUTPUT` provides a baseline export; use the host's Office workflow for professional master and appendix layout. Missing routing branch coverage or stale reviews block export.5. Use `research-codebook` to generate the matching Datamap. Check variable names, multi-response storage, matrix dimensions and missing rules; then inspect Office validity and layout.Do not invent incidence rates or quotas. Review marginal quota totals separately per dimension. Calibrate timing and quality rules through a pilot; do not assume one cutoff fits every study. Business review and fieldwork piloting remain required beyond the compiler checks.The original small `questionnaire --plan PLAN` workflow remains supported through [its legacy protocol](references/protocol.md). Prefer v2 for new studies.This skill requires the shared Python package installed from this repository. It does not run a web server or grant authority to publish or message anyone.

Frequently asked questions