Mk 059 logo

Mk 059

Community
backtrue
mk-059

Per-product contribution margin calculation. Use when the task requires the amount remaining after specified variable expenses. Apply this method to the specified inputs and verify the deliverable

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-059
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 059 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-059
  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-059 .claude/skills/mk-059
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 059 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 059 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 059 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-059 | Per-product contribution margin calculation

For a regular chat, upload packs/mk-059.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: The amount remaining after specified variable expenses

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

Required inputs

Provide: Unit net revenue, variable costs on the same unit basis and calculation scope

For method questions, provide the formula, variables and an example directly; for a calculation, ask only for missing operands

Method

  1. Calculate a product's contribution margin amount by subtracting its variable costs from revenue first
  2. Variable costs must include actual items such as purchasing/production, payment processing and logistics, revenue shares, taxes, and advertising incurred with sales
  3. Flag missing cost items as incomplete; do not pass off selling price minus purchase cost as the full contribution margin

Calculations and interpretation

Per-product contribution margin = net revenue per unit − variable costs for that unit

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

MK-059 supplementary method: contribution per eligible visitor

When comparing offers or comparable groups, first calculate each valid order's contribution using the same period and cost basis, then sum the group's contribution and divide by all eligible visitors in that group. Keep zero-order visitors in the denominator. If groups are defined by customer, use deduplicated customer counts; do not replace customers with order counts. If a visitor/customer has multiple orders, sum their in-scope orders using an attribution rule fixed in advance

Contribution per eligible visitor = total contribution from the group's valid orders ÷ all eligible visitors in the group. Revenue per visitor and contribution per visitor are different. When costs are incomplete, report only partial contribution; do not call revenue per visitor profit. Do not output contribution per visitor when the denominator is zero or missing

State the aggregation level and denominator, whether zero-order visitors are included, whether customers are deduplicated, and the completeness of costs Do not define additional purchases/incrementality solely as new customers; new versus existing customer status is not causal evidence. Comparing offer effects also requires a valid control or comparable baseline and sufficient observation time. Otherwise, report only an arithmetic scenario or observed difference

Revenue, discount, and refund basis: deduct each item only once

Establish the basis of the revenue input before writing the per-order contribution formula. If it is already net of discounts, do not deduct discounts again; if refunds have already reduced revenue, do not deduct them again. If the input is before discounts, subtract actual discounts once. If refunds are not yet reflected, subtract refunds that have occurred for the same order scope and observation period. If cost or refund data has not matured, report provisional/partial contribution rather than final profit

When "revenue" or "receipts" does not specify the treatment of discounts and refunds, do not choose a definition yourself. Provide two conditional formulas and identify the missing fields. Until the basis is confirmed, do not call one result complete contribution or profit

Supplementary acceptance cases

MK-059-C07 | The per-visitor denominator and boundaries of additional purchases Case data: Group A has 100 eligible visitors and total order contribution of 1,000 monetary units; Group B has 100 eligible visitors and total order contribution of 800 monetary units. Both denominators include eligible visitors who did not order Expected: Group A's contribution per visitor is 10 monetary units and Group B's is 8. Output the formula, denominator, and cost completeness. Without a visitor denominator, do not infer contribution per visitor. When assessing additional purchases, do not consider only new-customer counts or treat an arithmetic difference as causal proof

Supplementary method sources

  • Oracle Commerce experiment goals: Revenue per Visitor uses the number of participants in the group as its denominator. This supplementary method replaces the numerator with the order contribution calculated by this skill; it does not call Oracle's revenue metric a profit metric
  • Shopify Profit reports: used to check the definitions of net sales, costs, gross profit, discounts, and refunds
  • The contribution-per-visitor formula is a supplementary step written by ThinkWithBlack from the per-order contribution method; it is not claimed to be quoted verbatim from the sources above

Free-shipping comparisons: verify shipping revenue from buyers first; do not substitute logistics expense

Use this only when comparing shipping/free-shipping offers for the current task. The first deliverable must list knowns and unknowns: net product revenue excluding shipping P, the original shipping fee charged to the buyer F, the seller's payment to the logistics provider L, other costs C, and whether the receipts input already includes F. The seller's per-order shipping, logistics, or delivery cost can only be L. Statements such as "the buyer pays shipping", "below the free-shipping threshold", or "the seller absorbs shipping" do not supply the amount of F

If F or the receipts basis is missing, first state "The reduction in contribution from making existing orders ship free cannot currently be calculated." For the same orders that would have occurred anyway, holding product revenue, logistics expenses, and other costs constant: original contribution is P+F-L-C, new free-shipping contribution is P-L-C, and new minus original is -F. N existing orders lose N×F in receipts. L occurs in both offers and is neither an incremental cost nor its upper bound. Leave F symbolic when unknown; do not assume F=L, F≤L, or zero original net shipping revenue. Do not calculate a fixed loss, percentage decline, or break-even increase in orders from such assumptions

Even a purely hypothetical example must explicitly state "Assume additionally that the buyer originally paid shipping F = [amount], and product revenue excludes F" before substitution. Saying only "this is hypothetical" or "the customer pays shipping" is insufficient. Knowing L does not permit assuming the same F. Retain logistics expense in both old and new offers; do not write the old offer simply as product gross profit. Do not turn a hypothetical result into a currently known loss

Calculate additional orders separately as P-L-C; do not treat their partial contribution as the loss on existing orders. If receipts already include F, separate out P first; do not add F or deduct shipping twice. Identify partial contribution when costs such as payment processing or refunds are missing. After preserving unknowns, still complete segmentation and controlled-comparison design. The missing-input list must include the buyer's original shipping fee and whether receipts include shipping, not merely the order distribution

For free-shipping comparisons, follow the separate verification of revenue and expenses described above

Verification cases

MK-059-C05 | A required denominator is zero

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

MK-059-C06 | Only some costs are supplied

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

Method sources

Source file: 行銷策略實戰學程Day2-以終為始x降低成本x提升指標

Location: Costs

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1NdxlcqAKMPHqGVS5jbjSYR_UgOJSA0fS65OnTtQLEHQ/edit

English translation of source excerpt:

Begin with the end in mind x reduce costs x improve metrics

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 059 AI skill do?

Per-product contribution margin calculation. Use when the task requires the amount remaining after specified variable expenses. Apply this method to the specified inputs and verify the deliverable

Why use Mk 059 on TypingMind?

Because you install it once and use it with any model. Mk 059 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 059 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-059. 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 059?

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 059?

As many as you like. As long as a model supports skills, you can use Mk 059 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 059 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 👇