Mk 083 logo

Mk 083

Community
backtrue
mk-083

Plan post-purchase product sequences around existing buyers' needs so the same audience continues buying suitable products from the line. Use when second and third purchases are scarce, the user does not want to keep increasing ad spend, and wants a direction for follow-on purchases first

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-083
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 083 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-083
  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-083 .claude/skills/mk-083
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 083 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 083 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 083 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-083 | Product progression from first to repeat purchase

For a regular chat, upload packs/mk-083.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: The product path after the first purchase

Products occurring in the same transaction do not establish psychological motives; a product pairing does not automatically prove cross-selling effectiveness

Required inputs

Available raw records: first-purchase SKU, quantity, purpose and use, available products and costs, later orders, and product cycles

Method Steps

  1. Use first SKU, quantity, purpose, usage conditions, and later orders to find the next unmet need. For directional advice, propose conditional paths from existing products without requiring complete second/third-purchase metrics
  2. Choose replenishment for a consumable approaching an evidenced usage cycle. Choose cross-product continuation when a compatible accessory or next-stage need exists while the main product remains usable. Do not force an unrelated, already-owned, or incompatible margin product
  3. For both second and third purchases, ask what the previous order resolved and what remains needed. Exclude already purchased or unsuitable products, then inspect stock, contribution, and contact eligibility
  4. Time replenishment from actual quantity/use or product-specific intervals; time complementary products from the usage stage. Without cycle data, give a trigger and request product-use evidence rather than imposing 10–14 days
  5. Replace the next product or date after a new order, remaining stock, changed use, or return. If the planned second product has been bought, move only to the next evidenced need

Calculation and Interpretation

When measurement is requested, next-product purchase rate = people in the same first-purchase cohort buying that product within the same horizon / the complete original first-buyer group, including nonrepeat buyers. Report product mix among repeat buyers separately. Deliver product, fit evidence, trigger, exclusions, and revision record for each step

Check example (hypothetical): a printer buyer explicitly needs duplex binding and a compatible binding accessory exists, supporting a next-step candidate. A new order shows that accessory was bought; remove the promotion and schedule consumable replenishment only when actual usage supports it

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

Activation conditions and full question scope

Use this skill directly when the user wants follow-on purchase directions for existing customers or a progression from the first purchase to other brand products, including second and third purchases. The original method's ongoing purchases are not limited to the second order. Propose paths using the store's products, needs, and purchase data; a separate method named "third purchase" is not required

Real question Q005: "Sales have stalled, few customers buy a second or third time, and I don't want to keep increasing advertising investment. What direction could I take?" Original question. Preserve the constraint against continually increasing ads. A product progression is one applicable operating direction; the author's belief that ads are already optimized remains a self-report

Check SKUs, product costs, customer groups, purchase records, and product lines first. If unavailable, use the seven required fields to deliver conditional candidates, evidence of fit, and missing inputs; do not invent products, gross margins, cycles, or sales outcomes. Unless precise measurement is requested, do not make full-history segmentation or second-/third-purchase-rate calculations mandatory prerequisites

If the task is only to arrange a second product and reminder timing for someone who has bought once, use the first-buyer second-purchase planning method. If the request also includes cause diagnosis, actual repeat-purchase metrics, causal effects, loyalty programs, or platform configuration, retain every task and find the applicable methods; product progression cannot substitute for them. General operating advice is not a request to prove revenue has already increased; this skill does not promise an outcome

Verification cases

MK-083-C05 | One item has two distinct uses

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

Method sources

Source file: 營業額提升主要關鍵(一)縱深橫寬產品/產品線企劃策略

Location: Product

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1lIddPByRFVZeT-TR3CSaL_lEKkpJRloL6JQBLg1fO50/edit

English translation of source excerpt:

Product/product-line planning for depth and breadth

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 083 AI skill do?

Plan post-purchase product sequences around existing buyers' needs so the same audience continues buying suitable products from the line. Use when second and third purchases are scarce, the user does not want to keep increasing ad spend, and wants a direction for follow-on purchases first

Why use Mk 083 on TypingMind?

Because you install it once and use it with any model. Mk 083 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 083 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-083. 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 083?

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 083?

As many as you like. As long as a model supports skills, you can use Mk 083 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 083 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 👇