Skip to content
Back to skills

Mk 006

ASecurity

Prioritizing three lead selling points. Use when the task requires lead selling-point priorities and reasons for trade-offs. Apply this method to the specified inputs and verify the deliverable

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

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-006 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 006?

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

Security grade badge for Mk 006
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-006/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-006)

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-006
description: "Prioritizing three lead selling points. Use when the task requires lead selling-point priorities and reasons for trade-offs. Apply this method to the specified inputs and verify the deliverable"
---

# MK-006 | Prioritizing three lead selling points

For a regular chat, upload `packs/mk-006.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Lead selling-point priorities and reasons for trade-offs**

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

## Required inputs


Available raw records: candidate product claims, supporting evidence, customer choice or lost-sale records, and competitor conditions

## Method Steps

1. Link each candidate benefit to product facts, verifiable evidence, the customer's current job, and actual competitor differences. Exclude unsupported, irrelevant, or unfulfillable promises
2. Prioritize a condition that remarks or choice records show would block purchase, when the product can resolve it. If the product fails a necessary condition, change the offer rather than hiding the failure behind another attractive benefit
3. Compare the remaining known trade-offs. For equally relevant benefits, favor direct evidence and a perceptible difference. Shared basic features remain supporting points; without competitor evidence, state owned capability rather than exclusivity
4. Select up to three lead benefits addressing distinct important problems; deliver two if only two qualify. Internal votes express preference, not proof. If candidates cannot be distinguished, retain them and inspect an actual lost-sale/choice record or compare message response
5. Re-rank after customer-task, competitor, or evidence changes. Move a former lead to support or remove it when differentiation or fulfillment disappears, identifying the replacement and its evidence

## Calculation and Interpretation

For each benefit, deliver supporting fact → decision barrier resolved → lead/support/unresolved → reason another option was not selected → condition for changing rank. Do not invent weighted scores without established brand weights

Check example (hypothetical): a customer requires same-day pickup and verified stock exists, making pickup more relevant than packaging design. Stock updates show arrival in three days; remove the same-day promise despite its earlier internal vote count

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-006-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-006-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.md4.3 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json9.5 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.