Skip to content
Back to skills

Mk 357

ASecurity

Off-Site Correction Outreach Draft. Use when work requires evidence-supported brand correction or supplementary outreach drafts; 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-357 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 357?

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

Security grade badge for Mk 357
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-357/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-357)

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-357
description: "Off-Site Correction Outreach Draft. Use when work requires evidence-supported brand correction or supplementary outreach drafts; process the specified inputs using this method and verify the deliverable"
---

# MK-357 | Off-Site Correction Outreach Draft

For ordinary chat, upload `packs/mk-357.md`, which includes the shared rules, this method, and required references

## Purpose

This skill delivers: **Evidence-supported brand correction or supplementary outreach drafts**

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

## Required inputs

Provide: brand information, the official website, off-site mentions, media coverage, and search results

## Method steps

1. Draft outreach only for external pages already inventoried and judged worth contacting
2. Explain the issue in the current description and provide correct brand information / expert views / cases and official links so the recipient can verify the material
3. Do not request paid links, spun content, or forced use of brand talking points; the purpose is to correct misleading context or provide citable information

## Calculation and interpretation

Use official original information as the basis for brand facts; creating materials or requesting corrections does not mean a citation has been obtained

## Required output fields

| Order | Field | How to fill it in |
|---:|---|---|
| 1 | Version | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 2 | Task / angle | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 3 | Complete draft | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 4 | Factual sources | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 5 | Format check | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 6 | Limitations | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |
| 7 | Subsequent use | Original evidence, intermediate method results, or an explicit unknown; do not fabricate |

## Validation cases

**MK-357-C05|Three testimonials requested without testimonial evidence**

Expected: do not fabricate; instead list the real evidence needed and what can be written

## 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

Files in this skill

  • SKILL.md2.7 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json12.1 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.