Mk 352

---
name: mk-352
description: "Third-Party Content Improvement Priorities. Use when work requires priorities based on gaps, impact, and ability to act; process the specified inputs using this method and verify the deliverable"
---

# MK-352 | Third-Party Content Improvement Priorities

For ordinary chat, upload `packs/mk-352.md`, which includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Priorities based on gaps, impact, and ability to act**

Brand mentions, citations, and correct descriptions are different outcomes and cannot substitute for one another

## Required inputs


Available raw records: the actual external page and wording, inclusion criteria, customer questions, and original brand records supporting a correction

## Method Steps

1. Read actual third-party pages for core questions, recording brand placement, comparison criteria, exact errors, and supporting first-party records. Separate absence from inaccuracy
2. Prioritize correcting a statement that can mislead a material suitability, service, or product choice when corrective evidence exists. Mere absence supports a supplementary inclusion candidate only when the brand fits the article's scope
3. Unrelated tasks, failed inclusion criteria, or unsupported information lower priority or remove outreach. “Our brand is missing” is not sufficient for every page
4. Within a priority tier, compare documented reader-demand frequency, available exposure records, correction feasibility, and preparation cost. Unknown traffic or AI use remains unknown rather than becoming an impact score. Request the exact statement or inclusion rule that changes the tier
5. Re-rank after corrections, scope changes, or brand-data updates. Remove corrected pages from the correction list; lack of citation does not prove correction had no value or guarantee that more content will work

## Calculation and Interpretation

Deliver reader choice, current wording, direct evidence, correct/supplement/skip, priority reason, and removal condition. Prepare outreach drafts and evidence; actual contact follows user authorization

Check example (hypothetical): a comparison says the brand has no home service, while official records show service in that region, supporting correction priority. The article proves to cover offshore islands while service covers only the main island; withdraw the error label and high-priority outreach

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

## Required output fields

| Order | Field | How to fill it in |
|---:|---|---|
| 1 | Candidate | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 2 | Eligibility | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 3 | Relevant evidence | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 4 | Task fit | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 5 | Limitations / resources | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 6 | Priority | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 7 | Tradeoff rationale | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 8 | Missing items | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |

## Validation cases

**MK-352-C05｜Only two valid candidates exist**

Expected: deliver the two items and their limitations; do not invent other candidates to meet a quota

## Method sources

Original file: SEO105_Off-page_GEO

Source locator: brand

Source basis: extracted from course materials

Original URL: https://docs.google.com/presentation/d/1R3Q7M_pdyW1GbjDczTKK5ryfs5LrxGlNR5rjHpDjJUI/edit

English translation of source excerpt retained in the master sheet:

> Help AI understand your brand on the public web