Consulting Output Acceptance Questions. Use when work requires real case inputs and conditions for an acceptable result; process the specified inputs using this method and verify the deliverable
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Mk 450?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/backtrue-mk-450)
---
name: mk-450
description: "Consulting Output Acceptance Questions. Use when work requires real case inputs and conditions for an acceptable result; process the specified inputs using this method and verify the deliverable"
---
# MK-450 | Consulting Output Acceptance Questions
For ordinary chat, upload `packs/mk-450.md`, which includes the shared rules, this method, and required references
## Purpose
This skill delivers: **Real case inputs and conditions for an acceptable result**
Maintain, observe, and gather evidence first are valid decisions; do not conceal a lack of evidence behind a well-organized report
## Required inputs
Provide: Consultant task to accept, expected outputs and prohibited behavior, representative questions/inputs and known failure cases; design questions from these when no test set exists
## Method steps
1. Acceptance at the Do stage: required data, pages / modules to change, who provides data, and how completion will be checked
2. Acceptance at the Check stage: completed / insufficient items, changes in AI answers, changes potentially related to optimization, remaining problems, and adjustments to the next Plan
3. Validate the Plan rather than generating another question bank; do not attribute changes to optimization without evidence
## Calculation and interpretation
This task only inventories work; old specifications are not new authorization, and tools must actually be available before claiming execution
## Required output fields
| Order | Field | How to complete |
|---:|---|---|
| 1 | Acceptance question and scenario | Use the supplied source, calculation, or explicit unknown |
| 2 | Test inputs | Use the supplied source, calculation, or explicit unknown |
| 3 | Expected behavior and required output | Use the supplied source, calculation, or explicit unknown |
| 4 | Disallowed behavior | Use the supplied source, calculation, or explicit unknown |
| 5 | Pass/fail criteria | Use the supplied source, calculation, or explicit unknown |
| 6 | Evidence location | Use the supplied source, calculation, or explicit unknown |
| 7 | Execution status | Use the supplied source, calculation, or explicit unknown |
## Verification cases
**MK-450-A1 | Test merely says “answer well”**
Expected: Define observable required output/failure conditions with actual inputs
## Method sources
Original file: SEO 108|AI 搜尋顧問 GPT|Prompt 完整版講義
Source locator: consulting
Source basis: extracted from course materials
Original URL: https://docs.google.com/document/d/1UQVafPo3xVxC2PQ_muPU1qDKUo1M-WXH6A7dEVV5lJY/edit
English translation of source excerpt retained in the master sheet:
> You are an SEO / AEO / GEO performance diagnostic consultant specializing in helping brands review website content, AI citability, external brand context, and the search-to-sale path