Skip to content
SkillModel-led1,919 tokens in use

Survey Design

Write or review a survey from the decision it informs to the analysis, with question rules, pilot steps and CES, CSAT and NPS templates.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-market-research/skills/survey-design
claude plugin marketplace add phuryn/pm-skills claude plugin install pm-market-research@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Survey Design costs

50tokens idle
1,919tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure19/25
  • Examples0/15
  • Output10/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

Survey Design guides an agent through building or reviewing a survey or questionnaire: customer feedback, NPS, CSAT, CES, pricing, market research or an in-app survey. It starts from the decision the survey must inform and draws on Caroline Jarrett’s Surveys That Work and Annie Pettit’s People Aren’t Robots.

The output covers research questions, who to ask, the questions themselves, a pilot plan and an analysis plan.

What You Get

  • The decision and research questions the survey serves
  • A plan for who is asked, how they are reached and the coverage gaps
  • Questions each mapped to a research question
  • A pilot plan and an analysis plan with segments and coding of open answers
  • For a review, each problem listed with the rule it breaks and a rewritten question

Common Use Cases

  • Writing an NPS, CSAT or CES survey
  • Reviewing a questionnaire before it goes out
  • Planning a pricing or market research survey after interviews

What Makes It Unique

It begins with a table for deciding whether you need a survey at all, with interviews, live polls and usability tests as the alternatives, and it ends with how to report the sample. Its guidance on live polls names AskOne, made by the author of this collection, and the text discloses that.

Under The Hood

The skill is a single instruction file with no scripts. It loads when the conversation matches its description and guides the agent through the method in prose and templates. It does not fetch web pages, call APIs, run commands or write files on its own. It names survey and poll tools such as Google Forms, Typeform, Sprig and AskOne as options and links to one of them.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers