Survey Methodologist — Questionnaire Design, Review & Sampling
Turns your agent into a rigorous survey methodologist that designs, reviews, and fixes questionnaires — question wording, response scales, sampling, and data quality.
- Fix double-barreled questions and leading stems in draft instruments
- Optimize response options and anchors for higher reliability and better variance
- Design bot-detection, attention-check, and careless-responder screening with set thresholds
$19
· or 95 creditsSecure checkout via Stripe
Included in download
- Fix double-barreled questions and leading stems in draft instruments
- Design bot-detection, attention-check, and careless-responder screening with set thresholds
- file_read, file_write automation included
- Ready for Works in Claude Code
Media gallery
See it in action
You say
Review this survey question: "How satisfied are you with our service and pricing on a scale of 1-5 (1 = Extremely Dissatisfied, 5 = Extremely Satisfied)?"
Your agent does
Three fixes. (1) Double-barreled — "service" and "pricing" are two things; split them into two questions, since a respondent who feels differently about each can't answer cleanly and you won't know which drove the score. (2) Replace the "Extremely" anchors with "Very" — people avoid labeling themselves at an extreme, which compresses your variance. (3) Start the scale at the absence point for this unipolar construct: Very dissatisfied (0) → Dissatisfied (1) → Neither (2) → Satisfied (3) → Very satisfied (4), with "Prefer not to say" (-99) offset below. Result: two clean, single-idea items on a consistent scale.
Survey Methodologist — Questionnaire Design, Review & Sampling
Turns your agent into a rigorous survey methodologist that designs, reviews, and fixes questionnaires — question wording, response scales, sampling, and data quality.
$19
· or 95 creditsSecure checkout via Stripe
Included in download
- Fix double-barreled questions and leading stems in draft instruments
- Design bot-detection, attention-check, and careless-responder screening with set thresholds
- file_read, file_write automation included
- Ready for Works in Claude Code
- Instant install
Media gallery
See it in action
You say
Review this survey question: "How satisfied are you with our service and pricing on a scale of 1-5 (1 = Extremely Dissatisfied, 5 = Extremely Satisfied)?"
Your agent does
Three fixes. (1) Double-barreled — "service" and "pricing" are two things; split them into two questions, since a respondent who feels differently about each can't answer cleanly and you won't know which drove the score. (2) Replace the "Extremely" anchors with "Very" — people avoid labeling themselves at an extreme, which compresses your variance. (3) Start the scale at the absence point for this unipolar construct: Very dissatisfied (0) → Dissatisfied (1) → Neither (2) → Satisfied (3) → Very satisfied (4), with "Prefer not to say" (-99) offset below. Result: two clean, single-idea items on a consistent scale.
About This Skill
Most survey problems are baked in before the first response arrives: a double-barreled question, a scale that leads, a check-all list that quietly under-counts, a sample that can't support the claim you want to make. This skill gives your agent a working methodologist's judgment for catching those problems and fixing them. It's organized around Total Survey Error, so every recommendation traces back to whether it changes what you measured or who you reached. The core covers question wording, response-option design, scale selection, survey flow, and a pre-delivery QA checklist. Six reference files go deeper — question and scale design, the psychometrics of response options, reliability and validity, sampling and weighting, survey experiments, and a source-verified reading list — and the agent loads only what a task needs. Use it to design a new instrument, review a draft someone hands you, tighten weak items, choose an established scale, or size and plan a sample. It stays honest about what the evidence supports: conventions are labeled as conventions, cutoffs as guidance, and correlational data never gets causal language. Written for researchers, UX and market researchers, product and policy teams, nonprofits, and graduate students — anyone who fields a survey and needs the results to hold up.
Use Cases
- Fix double-barreled questions and leading stems in draft instruments
- Optimize response options and anchors for higher reliability and better variance
- Design bot-detection, attention-check, and careless-responder screening with set thresholds
- Size a sample from a precision or power target, adjusted for design effects
- Turn a fuzzy construct into clean items and a response scale that fits it
- Design a survey-embedded experiment with random assignment and a manipulation check
Known Limitations
Guides design and drafting; it doesn't run the statistical analysis of collected data.
Names established scales and their properties; it doesn't reproduce copyrighted scale items.
Conventions and cutoffs are starting points to reason from, not automatic pass/fail rules.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/survey-methodologist-questionnaire-design-review-sampling -o /tmp/survey-methodologist-questionnaire-design-review-sampling.zip && unzip -o /tmp/survey-methodologist-questionnaire-design-review-sampling.zip -d ~/.claude/skills && rm /tmp/survey-methodologist-questionnaire-design-review-sampling.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
Allowed Hosts
File Scopes
Pure Markdown guidance with no scripts, network calls, or secrets. It needs read access only to whatever draft or notes you give it; write access is optional if you want a revised draft saved to a file. It never needs terminal, browser, network, or environment-variable access.
Tags
Works in Claude Code, Cursor, Codex CLI, OpenClaw, and any SKILL.md-compatible agent. Pure Markdown with progressive disclosure (a core file plus reference files loaded on demand); no scripts, network, or setup. Best on frontier models, where the agent reasons over the methodology rather than pattern-matching.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
Cinematic Landing Page Builder
Turn any business URL into a high-end animated landing page with 4K AI assets and GSAP animations via Cloudflare.
Bounty Security Pattern Master Library — 399 Vulnerability Patterns
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.
cinematic-sites
Turn any basic business URL into a high-end cinematic landing page with AI-generated 4K assets and GSAP animations.