Mk 067 logo

Mk 067

Community
backtrue
mk-067

Calculate break-even ROAS from revenue and non-advertising expenses. Use for questions about which product costs to include, whether production and delivery alone suffice, how to incorporate monthly company fixed costs, and whether the lowest-priced variant can represent the whole range. For method questions, deliver cost definitions, formulas, and examples directly; check costs and sales mix when calculating actual figures. A break-even question alone does not trigger scaling or pricing workflows

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-067
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 067 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-067
  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-067 .claude/skills/mk-067
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 067 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 067 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 067 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-067 | Break-even return on ad spend calculation

For a regular chat, upload packs/mk-067.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: A threshold calculated using gross margin and the specified expense basis

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

Required inputs

For a method question, deliver the formula and an explicitly hypothetical example directly. An actual calculation requires net revenue, non-advertising expenses, and fixed expenses not yet included for the same period and product scope. For multiple variants, use quantities and revenue/costs per variant, or totals already aggregated using the actual mix. A break-even threshold alone does not require conversion rate, actual CPA, or budget utilization

Method

  1. Confirm the period, scope, and sources of revenue and non-advertising expenses; organize variant and overall amounts using the calculation sequence below
  2. Calculate pre-advertising available contribution. Subtract fixed expenses not yet included when they must also be covered, then calculate break-even ROAS
  3. Retain the formula, cost basis, sales mix, and excluded expenses; provide a method explanation or actual calculation as requested

Calculations and interpretation

If advertising is the only remaining expense to cover, break-even ROAS = 1 ÷ pre-advertising contribution margin ratio

Execution order for a break-even calculation

This section covers the break-even formula and method questions; check costs and calculate the threshold in order

  1. Fix the period, currency, and product/variant scope; first confirm whether revenue is net of discounts and refunds. For each variant, list net revenue Rᵢ, non-advertising expenses Vᵢ for the same scope, and their sources. Include the product, payment/logistics, fulfillment, and other costs the question needs covered, counting each once. Advertising expense is the ceiling being solved for; do not deduct it into Vᵢ first. If only purchase costs are supplied, deliver a partial threshold and retain the remaining expense gaps
  2. Calculate Cᵢ=Rᵢ−Vᵢ, then aggregate R=ΣRᵢ and C=ΣCᵢ using the actual sales mix. Multiply unit prices and unit costs by quantities sold first; do not multiply values already totaled for the period again. Check attribution of shared order expenses first so they are not deducted for every variant. Aggregate products, categories, and the entire store within their respective consistent scopes; actual advertising ROAS must use the same revenue scope
  3. When R and C are both positive and advertising is the only remaining expense, the threshold is R÷C=1÷(C÷R). Deliver variant-level and overall results, expense definitions, and sales mix first. When R is zero/negative or C is zero/negative, do not output a positive break-even threshold; explain that there is currently no positive advertising allowance or valid revenue basis. If fixed expenses also need covering, list same-scope fixed expenses F separately and check whether they are already in V. Calculate R÷(C−F) only when there is no duplicate deduction and C−F is positive. Label results excluding fixed expenses as advertising break-even for the expense scope used

The lowest selling price does not imply the lowest contribution margin ratio. Do not substitute the cheapest variant for the whole product mix or directly average variant ROAS thresholds. When sales mix is unknown, deliver variant thresholds and the overall formula. Calculate future mixes as explicitly assumed scenarios; do not treat historical mix as a guarantee of the future

Purely hypothetical teaching example: variant A has net revenue 100, non-advertising expenses 50, an allowance of 50, and a threshold of 2. Variant B has net revenue 200, non-advertising expenses 160, an allowance of 40, and a threshold of 5. Selling one of each gives an overall threshold of 300÷90=10/3, not (2+5)÷2=3.5. Lower-priced A actually has the lower threshold. If the question is only how to calculate it, these formulas and counterexample provide a complete answer; obtain actual variants, sales volumes, and expenses only when calculating for a specific store

Retain this skill's seven required output fields: input variable, value, unit and definition, source, formula, result, and limitations. Label teaching numbers as assumptions and keep unknown case values unknown. Do not omit the method answer because store-specific figures are missing

This section expands the existing reciprocal formula arithmetically. Separating non-advertising costs and fixed expenses refers to Shopify break-even calculation and FAQ. Aggregation across variants and the lowest-price counterexample are derivations for this method; they introduce no market threshold and are not presented as verbatim course content

Retain original values, units, periods, and substituted formulas. The formula is not an unconditional guarantee of results

Define gross profit, contribution margin, cost denominators, and periods explicitly; do not copy classroom example numbers as universal thresholds

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-067-C05 | A required denominator is zero

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

MK-067-C06 | Only some costs are supplied

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

Method sources

Source file: Meta廣告學程 104 廣告的數據決策

Location: ROAS

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/16FiqnSxBs-gSDxsxUBNhWdUX5vZrIWoZPGangj_f_Pk/edit

English translation of source excerpt:

Reasonable ROAS

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 067 AI skill do?

Calculate break-even ROAS from revenue and non-advertising expenses. Use for questions about which product costs to include, whether production and delivery alone suffice, how to incorporate monthly company fixed costs, and whether the lowest-priced variant can represent the whole range. For method questions, deliver cost definitions, formulas, and examples directly; check costs and sales mix when calculating actual figures. A break-even question alone does not trigger scaling or pricing workflows

Why use Mk 067 on TypingMind?

Because you install it once and use it with any model. Mk 067 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 067 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-067. 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 067?

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 067?

As many as you like. As long as a model supports skills, you can use Mk 067 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 067 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 👇