Mk 093 logo

Mk 093

Community
backtrue
mk-093

Organizing high- and low-season pacing. Use for historical seasonality hypotheses or seasonal ecommerce questions about peak-demand assumptions, annual planning, and end-of-season monitoring. Deliver conditional guidance for general method questions; mentions of PPC or CAC alone do not trigger account diagnosis

Overview

Publisherbacktrue
Repositorythinkwithblack-skill
Skill namemk-093
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 093 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-093
  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-093 .claude/skills/mk-093
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 093 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 093 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 093 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-093 | Organizing high- and low-season pacing

For a regular chat, upload packs/mk-093.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: Seasonality hypotheses grounded in historical data

Historical seasonality can inform planning but does not guarantee recurrence; do not create paid schedules or publish without user approval

When a seasonal ecommerce operator asks whether searches, auction competition, and conversions rise together, whether to cut budgets as end-of-season costs increase, and how to plan over the long term, use this method to examine seasonal hypotheses, events, and comparability and deliver an annual phase table. Check platform concepts against current official documentation. Treat general assumptions as hypotheses and provide method guidance without requiring account data. If the user separately requests diagnosis of an actual account, confirm the campaign type, valid outcomes, mature reporting period, and change history before handing off to the relevant method. Define brand queries separately from new-versus-existing customer identity, and platform CPA separately from new-customer CAC

Required inputs

Available raw records: dated sales and orders by product/channel, opening time, prices/promotions, stockouts, events, and advertising

Method Steps

  1. Gather dates, revenue, orders, opening days/hours, prices/promotions, stockouts, events, and advertising for matching products/channels. Align moving holidays to the same event stage
  2. Repeated directional demand changes across comparable cycles support a seasonality candidate. A single promotion or closure in one year is initially an event or supply explanation
  3. Consistent demand signals after considering operating time and available products support advance inventory, production, or calendar allocation. A peak without stock or capacity calls for supply preparation before added spend
  4. Without comparable history, deliver known event dates and demand scenarios rather than declaring a certain peak month. Request the matching-period record that distinguishes seasonality from an event
  5. Withdraw the seasonal label when closure, stock, or price explains the change. If the direction persists but magnitude changes, update quantity and budget scenarios rather than copying last year's percentages

Calculation and Interpretation

Report total revenue, comparable operating time, and orders/revenue per operating unit together. Normalization does not remove every difference; assess product, price, channel, and event comparability from records

Check example (hypothetical): monthly revenue falls from 300,000 to 150,000. Opening days also fall from 30 to 15, leaving 10,000 per day. Withdraw “demand halved” and plan around available operating capacity

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

Required output fields

OrderFieldHow to complete
1Comparison periods, product and channelUse the supplied source, calculation, or explicit unknown
2Raw revenue and ordersUse the supplied source, calculation, or explicit unknown
3Effective operating timeUse the supplied source, calculation, or explicit unknown
4Metric per unit of operating timeUse the supplied source, calculation, or explicit unknown
5Promotions, stockouts, price and other eventsUse the supplied source, calculation, or explicit unknown
6ComparabilityUse the supplied source, calculation, or explicit unknown
7Seasonal, event-related or unknown judgmentUse the supplied source, calculation, or explicit unknown
8Direction and revision conditionsUse the supplied source, calculation, or explicit unknown

Verification cases

MK-093-A1 | Revenue halves and operating days halve

Expected: Revenue per operating day is unchanged; withdraw a seasonal conclusion based only on totals

MK-093-A2 | Only one annual promotion rose

Expected: Identify promotion confounding rather than recurring seasonality

Method sources

Source file: 行銷策略實戰學程Day4-佈局獲利 × 節奏變現 × 轉單收割

Location: Annual

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/1dq3xqYVUnWvUCpzZKI91yDDOzvkyG0uHy3EOsOjtItA/edit

English translation of source excerpt:

Why learn to plan an annual schedule

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 093 AI skill do?

Organizing high- and low-season pacing. Use for historical seasonality hypotheses or seasonal ecommerce questions about peak-demand assumptions, annual planning, and end-of-season monitoring. Deliver conditional guidance for general method questions; mentions of PPC or CAC alone do not trigger account diagnosis

Why use Mk 093 on TypingMind?

Because you install it once and use it with any model. Mk 093 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 093 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-093. 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 093?

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 093?

As many as you like. As long as a model supports skills, you can use Mk 093 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 093 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 👇