Mk 040 logo

Mk 040

Community
backtrue
mk-040

Matching needs to ad formats. Use when the task requires task allocation across search, video, and other formats. Apply this method to the specified inputs and verify the deliverable

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-040
Stars
249
Forks
24
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by backtrue on GitHub. Read the source before you install it.

Installation

Install the Mk 040 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-040
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/backtrue/thinkwithblack-skill.git /tmp/thinkwithblack-skill
mkdir -p .claude/skills
cp -r /tmp/thinkwithblack-skill/en/skills/mk-040 .claude/skills/mk-040
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 040 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mk 040 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mk 040 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

MK-040 | Matching needs to ad formats

For a regular chat, upload packs/mk-040.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: Task allocation across search, video, and other formats

Task stages are analytical categories, not a claim that every customer follows the same path

Required inputs

Available raw records: actual customer queries or remarks, products/services, existing assets and pages, and feasible next actions

Method Steps

  1. Use actual queries, customer remarks, and existing pages to identify the job, missing answer, and acceptable next action. Separate search records from interviews; imagined queries are not observed search demand
  2. Consider search when an explicit query exists and the page answers it with a usable next step. Consider video when understanding the difference requires seeing a process and genuine demonstration assets exist
  3. Consider Demand Gen when the need arises during browsing and matching contextual assets and a destination exist. A PMax candidate also requires a defined valuable conversion, usable measurement, and fulfillable destination; wanting orders is insufficient
  4. When several formats fit, choose the first test by the missing contact point, assets, budget, and known costs. Without comparable costs, offer bounded tests rather than inventing one best format. Prepare the destination or narrow the promise if no useful next action exists
  5. If a supposed query proves to be internal speculation, downgrade search to an unverified candidate. If existing text and images already explain the product, video is no longer required. Request only a raw customer question or asset that distinguishes the candidates

Calculation and Interpretation

Deliver the chain: customer wording → needed answer → format → existing asset/page → initial action. Separate format fit from advertising performance

Check example (hypothetical): repeated questions about how installation works plus a real demonstration support video. Raw remarks instead reveal questions about local installation availability; switch to a service-area page serving those explicit queries

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

Required output fields

OrderFieldHow to complete
1Source itemUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
2Target itemUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
3Supporting taskUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
4Evidence of fitUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
5Applicable conditionsUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
6Unmatched items/conflictsUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
7Next stepUse source evidence, an intermediate method result, or an explicit unknown; do not invent information

Verification cases

MK-040-C05 | One item has two distinct uses

Expected: List the uses and conditions separately; do not force a single match

Method sources

Source file: Google Ads 第一堂|看懂需求,才知道廣告怎麼接

Location: Ad formats

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/15ZOg0pX_xikpdA3FwGEoCSVgWortvCnxSe4hz4ugizg/edit

English translation of source excerpt:

Chapter 3 | Ad formats

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mk 040 AI skill do?

Matching needs to ad formats. Use when the task requires task allocation across search, video, and other formats. Apply this method to the specified inputs and verify the deliverable

Why use Mk 040 on TypingMind?

Because you install it once and use it with any model. Mk 040 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mk 040 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-040. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mk 040?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mk 040?

As many as you like. As long as a model supports skills, you can use Mk 040 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 040 AI skill free?

Yes. It is published on GitHub by backtrue under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇