Skip to content
Back to skills

Mk 017

ASecurity

Interpreting customers' core values. Use when the task requires what customers value and the original evidence for it. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added October 23, 2026
ai-agentsgogit

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-017 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 017?

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

Security grade badge for Mk 017
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-017/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-017)

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-017
description: "Interpreting customers' core values. Use when the task requires what customers value and the original evidence for it. Apply this method to the specified inputs and verify the deliverable"
---

# MK-017 | Interpreting customers' core values

For a regular chat, upload `packs/mk-017.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **What customers value and the original evidence for it**

Hypotheses are useful but do not establish demographics or market share; do not fabricate interview content or customer experiences

## Required inputs


Available raw records: actual choices and remarks, feasible alternatives, prices, delivery, quality, and availability at the time

## Method Steps

1. Preserve feasible alternatives, prices, delivery, quality, availability, actual choices, and remarks. First exclude unavailable options or those failing necessary conditions
2. A choice supports a contextual value priority only when feasible alternatives involve a real trade-off. Buying a cheaper item when the premium one is unavailable does not establish price priority; paying more to meet a deadline may support timing priority
3. When stated preference and behavior differ, inspect constraints rather than alleging dishonesty or inferring personality. Different tasks with different trade-offs remain separate conditions
4. Translate supported trade-offs into observable signals and messaging, such as prioritizing delivery evidence when people ask about dates and pay more under comparable terms. Demographics alone leave a hypothesis; request one complete choice record
5. Withdraw the value inference if no alternative was actually available or someone else made the decision. Opposite choices narrow the applicable context rather than changing a permanent personality label

## Calculation and Interpretation

Deliver options/constraints, observed trade-off, supported contextual value, matching message, and a potentially contradicting record. Do not score values from income or age

Check example (hypothetical): choosing next-day delivery at 1,500 over five-day delivery at 1,200 supports timing priority for that purchase. Records showing both were next-day and the cheaper item was unavailable withdraw the timing inference from price

Decision rules authored by ThinkWithBlack, 2026-10-14; original course sources remain below

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Hypothesized group | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 2 | Buying/using role | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 3 | Trigger situation | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 4 | Tasks and concerns | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 5 | Supporting clues | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 6 | Counterexamples | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 7 | Items to validate | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 8 | Suitable message | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |

## Verification cases

**MK-017-C05 | An order contains maternity and baby products**

Expected: Do not immediately identify the buyer as a mother; separate the buying and using roles

**MK-017-C06 | Different clues support two situations**

Expected: Keep both candidates and request the data that would distinguish them

## Method sources

Source file: 行銷策略實戰學程Day1-小眾就是大眾 × 精準 Persona × 數位資產

Location: Persona

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/11Jecvwonn6oA3y3zexPkNOv0iAJuL_7uqERiSNexjjw/edit

English translation of source excerpt:

> Niches form the mass market × precise Personas × digital assets

Files in this skill

  • SKILL.md4.2 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json8.9 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.