Mk 005

---
name: mk-005
description: "Selling-point evidence matching. Use when the task requires a claim, evidence, and gap comparison table. Apply this method to the specified inputs and verify the deliverable"
---

# MK-005 | Selling-point evidence matching

For a regular chat, upload `packs/mk-005.md`. It includes the shared rules, this method, and required references

## Purpose

This skill delivers: **A claim, evidence, and gap comparison table**

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

## Required inputs


Available raw records: the exact claim, product/version and conditions, full original evidence, comparator, measurement method, and outcome

## Method Steps

1. Make the claim checkable by specifying subject/version, conditions, comparator, outcome, and period. Read the source content and measurement method rather than treating a title, award, or brand name as support
2. A matching product and use condition directly measuring the claimed outcome supports that scope. Partial evidence calls for narrowing; evidence for another model or quantity does not transfer the full effect
3. “Better than others” requires comparable subjects and measurement. A testimonial supports that person's experience, not a universal guarantee or precise improvement percentage. If the function is supported but the number is not, retain a functional claim
4. Contradictory evidence withdraws the claim; an absent source leaves it unresolved. Request the original passage or report most likely to support the core statement, not more unrelated endorsements
5. Re-map claims after product-version, measurement-condition, or source revisions. Remove unsupported wording and supply a still-supported version

## Calculation and Interpretation

For each claim, record source location, supported scope, unsupported portion, usable wording, and replacement condition. An improvement calculation must show the original baseline and comparable difference; do not confuse relative percentages with percentage points

Check example (hypothetical): a report testing model A for ten continuous indoor hours does not prove ten outdoor hours for model B. Corrected data identifying the same model A and indoor context supports a narrowly conditioned statement

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

## Required output fields

| Order | Field | How to complete |
|---:|---|---|
| 1 | Original claim | Use the supplied source, calculation, or explicit unknown |
| 2 | Evidence source and location | Use the supplied source, calculation, or explicit unknown |
| 3 | Applicable audience, version and conditions | Use the supplied source, calculation, or explicit unknown |
| 4 | Supported scope | Use the supplied source, calculation, or explicit unknown |
| 5 | Unsupported or contradicted portion | Use the supplied source, calculation, or explicit unknown |
| 6 | Publishable revision | Use the supplied source, calculation, or explicit unknown |
| 7 | Supported, pending or withdrawn | Use the supplied source, calculation, or explicit unknown |
| 8 | Revision and recheck conditions | Use the supplied source, calculation, or explicit unknown |

## Verification cases

**MK-005-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-005-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