Skip to content
Back to skills

Mk 055

ASecurity

Design survey questions that distinguish reasons for choosing products. Use for post-purchase e-commerce customer insights, question recommendations, and research into pain points, needs, and product features. Deliver an evidence-based question draft first; derive specific options from real products and situations

  • 259 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 23, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 23, 2026

npx -y skills add backtrue/thinkwithblack-skill --skill mk-055 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 055?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Mk 055
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-055/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-055)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: mk-055
description: "Design survey questions that distinguish reasons for choosing products. Use for post-purchase e-commerce customer insights, question recommendations, and research into pain points, needs, and product features. Deliver an evidence-based question draft first; derive specific options from real products and situations"
---

# MK-055 | Product-preference question design

For a regular chat, upload `packs/mk-055.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Questions that distinguish reasons for choosing a product**

Without raw survey responses, produce only a questionnaire or analysis plan; do not fabricate answers

## Required inputs

Provide the decision the research supports, actual product facts, target respondents, and questioning context. Include existing customer wording when available; prior responses are not a prerequisite for designing questions

## Method

1. Break the research decision into purchase reasons, barriers, and usage needs to distinguish; give each question one purpose
2. Write neutral questions from actual product facts and context. Ask about choices or experience before reasons, with one issue per question; do not present brand assumptions as established needs
3. Specify single-choice, multiple-choice, or open responses. Resolve overlapping options, include other/not-applicable when useful, and base skip logic on actual experience
4. Deliver questions with option sources, then check an applicable and a non-applicable scenario for answerability. Use only the user's specified arrangements for lead collection or incentives

## Calculations and interpretation

Questions should distinguish answers that would change the decision. Avoid leading wording, double-barreled questions, and assuming a purchase. Before collection, deliver questions and checks without inventing sample sizes, preference shares, or purchase conclusions

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Question ID/purpose | Use the supplied source, calculation, or explicit unknown |
| 2 | Question text | Use the supplied source, calculation, or explicit unknown |
| 3 | Options and sources | Use the supplied source, calculation, or explicit unknown |
| 4 | Response format | Use the supplied source, calculation, or explicit unknown |
| 5 | Respondent and timing | Use the supplied source, calculation, or explicit unknown |
| 6 | Skip logic and checks | Use the supplied source, calculation, or explicit unknown |
| 7 | Missing evidence | Use the supplied source, calculation, or explicit unknown |

## Verification cases

**MK-055-A1 | Only product specifications are supplied for a post-purchase survey**

Expected: Deliver draft questions, option sources, and response formats without requiring prior responses

**MK-055-A2 | A question asks whether cheap and easy-to-use features caused liking**

Expected: Separate the reasons or use a neutral open question instead of combining two claims

## Method sources

Source file: 行銷策略實戰學程Day4-佈局獲利 × 節奏變現 × 轉單收割

Location: Survey

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1dq3xqYVUnWvUCpzZKI91yDDOzvkyG0uHy3EOsOjtItA/edit

English translation of source excerpt:

> Collect first-party data through surveys

Files in this skill

  • SKILL.md3.3 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json11.9 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.