Skip to content
Back to skills

Mk 004

ASecurity

Customer-value check for selling points. Use when the task requires the customer benefit associated with each selling point. Apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 4 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-004 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 004?

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

Security grade badge for Mk 004
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-004/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-004)

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-004
description: "Customer-value check for selling points. Use when the task requires the customer benefit associated with each selling point. Apply this method to the specified inputs and verify the deliverable"
---

# MK-004 | Customer-value check for selling points

For a regular chat, upload `packs/mk-004.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **The customer benefit associated with each selling point**

Separate features, benefits, and evidence; do not claim exclusivity without competitor data

## Required inputs


Available raw records: the proposed claim, product specifications or tests, actual customer questions, and usage conditions

## Method Steps

1. Break the claim into product capability, conditions where it works, and the user's resolved problem or completed task. Support the capability with specifications/tests and the task with customer records
2. Keep a capability directly serving a known task as a value proposition. A true but irrelevant feature becomes supporting information or a different angle. Narrow an effect exceeding its evidence to the supported scope
3. The word “you” is not a pass condition. A clear task can work without it; repeated “you” without an observable result still needs revision
4. With missing context, give a conditional version using known situations and request one customer question or usage record. Missing capability evidence leaves the claim unresolved rather than validated by fluent copy
5. Withdraw the lead benefit when new evidence invalidates the context or effect. Reconnect the benefit when the customer task changes instead of retaining the same persona assumption

## Calculation and Interpretation

Deliver original claim, product fact, customer task, supported outcome, retain/rewrite/remove, and revision evidence. Numerical benefits must map to measurement under matching conditions

Check example (hypothetical): ten-hour battery evidence under matching use conditions supports avoiding charging during an eight-hour field shift. For a permanently plugged-in desk worker, move it to supporting specifications rather than leading with a field-work benefit

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

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Factual feature | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 2 | Customer task | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 3 | Tangible benefit | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 4 | Basis for comparison | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 5 | Suitable angle | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 6 | Lead/supporting/to investigate | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |
| 7 | Reason | Use source evidence, an intermediate method result, or an explicit unknown; do not invent information |

## Verification cases

**MK-004-C05 | The specification is true, but no industry comparison data is available**

Expected: Functional benefits may be proposed; do not claim the product is unique or number one

**MK-004-C06 | The information consists only of technical terms**

Expected: Explain their role under the known usage conditions first; do not invent unverified effects

## Method sources

Source file: Meta廣告學程 101 讓AI幫你投出廣告

Location: USP

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/19GaScd4rGE8V4iqPfemeK8-QAwbSIeOKGpB5OwwTMlo/edit

English translation of source excerpt:

> Help identify the product's USP (Unique Selling Proposition). This is also your first opportunity to communicate with the AI. It is good if it identifies the point, but if it does not get what you mean, make sure to tell it your thinking

Files in this skill

  • SKILL.md4.1 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json10.9 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.