agentsclimarketplace

Design customer feedback survey

Skill alexe-ev/product-plugins/customer-success/skills/design-customer-feedback-survey

Skill library for AI agents — 15 product domains, 121 skills. Tells the agent what to ask, how to reason, and what to output.

Install
npx -y skills add alexe-ev/product-plugins --skill design-customer-feedback-survey

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design a customer feedback survey that generates reliable, actionable data. Use this skill when a team needs to collect structured feedback at scale without the bias and noise that comes from poorly designed surveys.

SKILL.md

2.6 KB, as published. Nobody here has run it

Design Customer Feedback Survey

Purpose

Help teams design surveys that generate valid, reliable feedback — avoiding common biases, measuring the right things, and producing data that can drive decisions.

Skill type

Conceptual skill

Use this skill when

  • A team needs to measure user satisfaction, NPS, CSAT, or feature feedback at scale
  • A survey exists but produces low response rates or uninformative data
  • A new product or feature launch needs a feedback collection mechanism
  • Periodic customer feedback needs to be standardized

Do not use this skill when

  • The goal is qualitative depth (use run-user-interviews instead of a survey)
  • The goal is synthesizing already-collected feedback (use synthesize-feedback-themes)

Required inputs

  • Survey goal: what decision will this survey inform?
  • Target respondents

Optional inputs

  • Prior survey designs or results
  • Feedback frequency requirements
  • Tooling constraints (Typeform, Google Forms, in-app survey tool)
  • Regulatory constraints on data collection

Upstream context

Works best when:

  • VoC program is defined
  • Key feedback questions are known

Downstream handoff

Output can feed:

  • synthesize-feedback-themes (survey responses → theme synthesis)
  • monitor-adoption-health (satisfaction metrics → health score input)
  • detect-performance-signals (survey scores → performance signals)

Instructions

  1. Define the one primary question this survey must answer.
  2. Select the appropriate survey type: NPS, CSAT, CES, feature satisfaction, or custom.
  3. Design survey questions: start with broad, then specific; close-ended before open-ended.
  4. Write each question to be unambiguous, unbiased, and answerable.
  5. Keep the survey to 5 questions or fewer for any single session.
  6. Define distribution: in-app trigger, email, post-interaction.
  7. Define analysis plan before launching.

Output

Provide:

  • Primary survey question
  • Survey type and rationale
  • Question set (5 or fewer)
  • Question quality review (bias check)
  • Distribution plan and trigger logic
  • Expected response rate and sample size
  • Analysis plan

Risks / caveats

  • Leading questions produce useless data — review each question for bias
  • Surveys longer than 5 questions have dramatically lower completion rates
  • Don't survey without knowing how you'll use the data

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.