What do I need to use Survey Design Basics?

The decision the survey feeds; The audience and reach method; The draft questions, if any; Prior interview themes.

Is Survey Design Basics free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Survey Design Basics

Q: How do I know the Survey Design Basics output is good?

The skill verifies itself against its own quality checks: No question telegraphs its hoped-for answer; Zero double-barrels survived; Every scale has honest exits and consistent direction; Every surviving question maps to a decision; the cut list exists.

🔵 Stable🕐 updated 2026-07-19 🔷 SkillSpec L3 pm-cowork

Design a survey that measures instead of leads — neutral question wording, answer scales that don't smuggle conclusions, the length that respects completion rates, and the analysis plan written before launch. Use when asked write our customer/employee survey, check these questions for bias, why are our survey results useless, or design the questionnaire for this decision. Produces the question set with bias fixes, the scale choices, the pilot step, and the pre-launch analysis plan.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The decision the survey feeds — what will be done differently based on results; questions that inform no decision get cut first ([kpi-tracker-design](../kpi-tracker-design/SKILL.md) so-what logic)

▸The audience and reach method — who gets it, how, and the response-rate reality (the selection caveat gets written into the analysis plan now, not discovered later)

▸The draft questions, if any — existing drafts get the bias audit; the classic sins are findable and fixable

▸Prior interview themes — surveys size what interviews surfaced ([interview-synthesis](../interview-synthesis/SKILL.md) hands off here); a survey inventing its own hypotheses mid-questionnaire does both jobs badly

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓No question telegraphs its hoped-for answer

✓Zero double-barrels survived

✓Every scale has honest exits and consistent direction

✓Every surviving question maps to a decision; the cut list exists

✓The analysis plan predates the launch

⚠️ What it refuses to do

Do not lead — a survey that flatters its author measures the flattery

Do not force answers — missing "don't know" manufactures opinions from noise

Do not ask everything interesting — length is paid in completion bias

Do not launch without the analysis plan — unanalyzable questions are respondent-time theft

Do not report percentages without the selection caveat — who answered is half the result

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="survey-design-basics"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Survey Design Basics is one of 750 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog