Skip to content
Back to skills

Mk 364

ASecurity

AI Brand Description Accuracy Check. Use when work requires checks against original brand information; process the specified inputs using this method 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-364 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 364?

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

Security grade badge for Mk 364
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-364/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-364)

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-364
description: "AI Brand Description Accuracy Check. Use when work requires checks against original brand information; process the specified inputs using this method and verify the deliverable"
---

# MK-364 | AI Brand Description Accuracy Check

For ordinary chat, upload `packs/mk-364.md`, which includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Checks against original brand information**

One answer does not establish a stable ranking; do not simulate current results when actual answers have not been obtained

## Required inputs

Provide: Original AI response, question, platform and date, plus approved brand name, category, products/services, positioning and sources

## Method steps

1. Check AI statements about brand name, type, services, positioning and differences, preserving the answer/source
2. For vague statements, compare approved name, category, audience, products and differentiation evidence directly; for errors, inspect actual citations/external descriptions
3. Report support, contradiction or unknown for each claim and the next evidence needed without inferring a cause from one error

## Calculation and interpretation

Retain questions, dates, platforms, and actual answers; one result does not represent answers shown to all users

## Required output fields

| Order | Field | How to fill it in |
|---:|---|---|
| 1 | Subject / location | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 2 | Conditions for use | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 3 | Actual evidence | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 4 | Check status | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 5 | Differences / possible causes | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 6 | Next task | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 7 | Limitations | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |

## Verification cases

**MK-364-A1 | Only AI answer, no approved brand facts**

Expected: List identity claims/source gaps rather than assume correctness

## Method sources

Original file: SEO 106|Check 成效診斷:從 AI 回答結果看出內容與品牌缺口

Source locator: questions

Source basis: extracted from course materials

Original URL: https://docs.google.com/presentation/d/1yJsbQNDgX4lUtExwfxXgaPvHjEwbjywvCKllchkIoOU/edit

English translation of source excerpt retained in the master sheet:

> • In what types of questions does it appear?

Files in this skill

  • SKILL.md2.7 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json16.3 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.