Mk 341

---
name: mk-341
description: "Before-and-After Article Revision Comparison. Use when work requires changes, retained facts, and items still lacking evidence; process the specified inputs using this method and verify the deliverable"
---

# MK-341 | Before-and-After Article Revision Comparison

For ordinary chat, upload `packs/mk-341.md`, which includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Changes, retained facts, and items still lacking evidence**

General content rewriting differs from Speak Human TW language review; do not automatically apply its review documents without an explicit trigger

## Required inputs

Provide: the full article, reader questions, sources, and actual experience or evidence

## Method steps

1. Before revising, save the first analysis, the weakest 3 checkpoints, and the original passages
2. Revise the gaps, run a second analysis, and save the results after revision
3. Deliver a before-and-after comparison and one sentence explaining why AI citation was previously difficult; do not report only an improved score

## Calculation and interpretation

Check only presence and clarity; do not invent experts, experience, or data, or guarantee AI citations

## Required output fields

| Order | Field | How to fill it in |
|---:|---|---|
| 1 | Comparison item | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 2 | Subject / version A | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 3 | Subject / version B | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 4 | Definition / basis | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 5 | Comparability | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 6 | Difference | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 7 | Source | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 8 | Limitations | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |

## Validation cases

**MK-341-C05｜Comparison periods differ in length or definition**

Expected: Do not directly compare totals; first list what is not comparable and what can safely be compared

## Method sources

Original file: SEO104_AI可引用文章檢查表

Source locator: checks

Source basis: extracted from course materials

Original URL: https://docs.google.com/presentation/d/1hmaWbUWe-BsaRUVA9IpGrLUt7wQ8wdIVHe4W_Sg4uP4/edit

English translation of source excerpt retained in the master sheet:

> The task of 104: check whether an article has the conditions needed for AI citation