Skip to content
Back to skills

Mk 257

ASecurity

Product Category Mapping. Use when you need mappings between internal and platform categories; apply this method to the specified inputs and verify the deliverable

  • 259 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 23, 2026
ai-agentsgoperformance

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-257 --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mk 257?

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

Security grade badge for Mk 257
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/backtrue-mk-257/badge)](https://www.skillsdirectory.com/skills/backtrue-mk-257)

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-257
description: "Product Category Mapping. Use when you need mappings between internal and platform categories; apply this method to the specified inputs and verify the deliverable"
---

# MK-257|Product Category Mapping

For a regular chat, upload `packs/mk-257.md`; it includes the shared rules, this method, and required references

## Purpose

This Skill delivers: **Mappings between internal and platform categories**

When IDs cannot be matched one-to-one, leave them unmatched rather than guess; do not invent a match rate without complete event samples

## Required Inputs

Provide: product Feed, actual website information, SKU performance, and disapproval messages

## Method Steps

1. Use google_product_category / fb_product_category and product_type to describe product categories
2. product_type can use breadcrumb levels, for example “Home > Womenswear > Dresses > Ankle-length dresses”
3. Categories must match the actual product and support later collection/catalog ad filtering; do not classify arbitrarily just to fill fields

## Calculation and Interpretation

Use product data for specifications and prices; verify catalog fields and disapproval rules during production

## Required Output Fields

| Order | Field | How to fill it |
|---:|---|---|
| 1 | Source subject | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 2 | Target subject | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 3 | Task to address | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 4 | Evidence of fit | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 5 | Applicable conditions | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 6 | Unmapped items / conflicts | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |
| 7 | Next step | Original evidence, intermediate method result, or explicitly unknown; do not fabricate |

## Verification Cases

**MK-257-C05|One subject has two different uses**

Expected: list uses and conditions separately rather than force a single match

## Method Sources

Original file: Meta廣告學程 105 有轉換是業績擴大的開始

Source location: Products

Source basis: Derived from course material

Original URL: https://docs.google.com/presentation/d/1RzfmYLhPsK23uxqxWbKji2-efsbJPGFs_tMzCRX56BM/edit

English translation of source excerpt retained in the master table:

> From product planning to catalog ads and collections, improve performance through budget allocation

Files in this skill

  • SKILL.md2.6 KB
  • assets/check-context.py14.6 KB
  • assets/context-contract.json8.5 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.