Skip to content
Back to skills

Mk 016

ASecurity

Persona candidate creation. Use when the task requires audience hypothesis cards that do not fabricate real identities. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 6 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-016 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 016?

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

Security grade badge for Mk 016
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-016/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-016)

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-016
description: "Persona candidate creation. Use when the task requires audience hypothesis cards that do not fabricate real identities. Apply this method to the specified inputs and verify the deliverable"
---

# MK-016 | Persona candidate creation

For a regular chat, upload `packs/mk-016.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Audience hypothesis cards that do not fabricate real identities**

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

## Required inputs

Provide: Product facts, existing customer data, surveys, or customer-service records

## Method

1. A Persona includes at least a name, age, place of residence, occupation, income, three product-selection values, three purchase motivations, preferred brands/competitors, and a short 5W1H story
2. Confirm the three USPs, average order value, and purchase frequency first, then infer candidate Personas using willingness-to-pay clues
3. One product can have multiple Personas. AI outputs are candidates that must subsequently be checked against paid traffic and actual data

## Calculations and interpretation

Treat customer roles and motivations as hypotheses initially; do not establish someone's actual identity from a single purchase behavior

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Persona name | Use the supplied source, calculation, or explicit unknown |
| 2 | Age, residence, occupation and income | Use the supplied source, calculation, or explicit unknown |
| 3 | Three values | Use the supplied source, calculation, or explicit unknown |
| 4 | Three motivations | Use the supplied source, calculation, or explicit unknown |
| 5 | Preferred brands and competitors | Use the supplied source, calculation, or explicit unknown |
| 6 | Who, When, Where, What, Why and How | Use the supplied source, calculation, or explicit unknown |
| 7 | Source, hypothesis or unknown for each item | Use the supplied source, calculation, or explicit unknown |
| 8 | Validation tasks | Use the supplied source, calculation, or explicit unknown |

## Verification cases

**MK-016-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-016-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.md2.9 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.