Mk 075 logo

Mk 075

Community
backtrue
mk-075

Cost-metric definition review. Use when the task requires a check for mixed use of leads, people, and orders. Apply this method to the specified inputs and verify the deliverable

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-075
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 075 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-075
  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-075 .claude/skills/mk-075
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 075 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 075 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 075 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-075 | Cost-metric definition review

For a regular chat, upload packs/mk-075.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: A check for mixed use of leads, people, and orders

Recalculability does not mean the data is complete; break-even points and cost ceilings apply only under the stated assumptions

Required inputs

Raw inputs: requested metric, expense scope, clicks, valid deduplicated leads, valid orders, buyers/new-customer keys, period, currency, attribution and validity definitions

Method

  1. Name the outcome as clicks, leads, orders, buyers or new customers and map each to a source field. First purchasers are not leads and buyer counts are not order counts; correct existing mislabeled formulas and denominators
  2. Click cost uses matching spend/clicks; lead cost matching spend/valid deduplicated leads; order cost matching spend/valid deduplicated orders. Buyer cost and new-customer CAC use their respective counts, with CAC expenses scoped as specified
  3. Before combining sources verify period, currency, click definitions and expenses. Mixing outbound and incompatible all-click counts is not one CPC. Deduplicate overlapping platform-attributed purchases using valid order keys or report platform values separately
  4. Zero denominators mean report spend and zero outcomes with undefined cost. Missing sources/partial costs retain partial values and missing items. Without validity rules report raw fields rather than infer sale, cancellation or new-customer definitions
  5. Deliver numerator, denominator, population, period, currency, deduplication and result for each metric. Recompute relevant values after orders, refunds, identity coverage or attribution corrections, retaining prior values and change sources

Calculations and interpretation

Hypothetical check with approved common spend 600: 300 matching clicks, 20 valid leads, 6 valid orders, 5 buyers and 3 new customers yield 2/click, 30/lead, 100/order, 120/buyer and 200/new customer. Different outcome definitions cannot be compared as deterioration in the same task

Decision rules authored by ThinkWithBlack on 2026-10-14; original course sources are retained below

Required output fields

OrderFieldHow to complete
1Input variableUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
2ValueUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
3Unit and definitionUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
4SourceUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
5FormulaUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
6ResultUse source evidence, an intermediate method result, or an explicit unknown; do not invent information
7LimitationsUse source evidence, an intermediate method result, or an explicit unknown; do not invent information

Verification cases

MK-075-C05 | A required denominator is zero

Expected: Report that the formula is undefined; do not output a zero cost or an infinite target

MK-075-C06 | Only some costs are supplied

Expected: Retain the partial result and excluded items; do not call it complete profitability

Method sources

Source file: LookerStudio教學

Location: Formulas for each metric

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/15dCCATrfSb0jHMhvfvp-15aQ5CvYW9xafHYPGm_pm3o/edit

English translation of source excerpt:

Formulas for each metric

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 075 AI skill do?

Cost-metric definition review. Use when the task requires a check for mixed use of leads, people, and orders. Apply this method to the specified inputs and verify the deliverable

Why use Mk 075 on TypingMind?

Because you install it once and use it with any model. Mk 075 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 075 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-075. 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 075?

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 075?

As many as you like. As long as a model supports skills, you can use Mk 075 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 075 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 👇