Mk 005

Community

backtrue

mk-005

Selling-point evidence matching. Use when the task requires a claim, evidence, and gap comparison table. Apply this method to the specified inputs and verify the deliverable

Overview

Publisher	backtrue
Repository	`thinkwithblack-skill`
Skill name	`mk-005`
Stars	249
Forks	24
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

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 005 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-005
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.

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-005 .claude/skills/mk-005

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mk 005 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 005 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 005 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-005 | Selling-point evidence matching

For a regular chat, upload packs/mk-005.md. It includes the shared rules, this method, and required references

Purpose

This skill delivers: A claim, evidence, and gap comparison table

Separate features, benefits, and evidence; do not claim exclusivity without competitor data

Required inputs

Available raw records: the exact claim, product/version and conditions, full original evidence, comparator, measurement method, and outcome

Method Steps

Make the claim checkable by specifying subject/version, conditions, comparator, outcome, and period. Read the source content and measurement method rather than treating a title, award, or brand name as support
A matching product and use condition directly measuring the claimed outcome supports that scope. Partial evidence calls for narrowing; evidence for another model or quantity does not transfer the full effect
“Better than others” requires comparable subjects and measurement. A testimonial supports that person's experience, not a universal guarantee or precise improvement percentage. If the function is supported but the number is not, retain a functional claim
Contradictory evidence withdraws the claim; an absent source leaves it unresolved. Request the original passage or report most likely to support the core statement, not more unrelated endorsements
Re-map claims after product-version, measurement-condition, or source revisions. Remove unsupported wording and supply a still-supported version

Calculation and Interpretation

For each claim, record source location, supported scope, unsupported portion, usable wording, and replacement condition. An improvement calculation must show the original baseline and comparable difference; do not confuse relative percentages with percentage points

Check example (hypothetical): a report testing model A for ten continuous indoor hours does not prove ten outdoor hours for model B. Corrected data identifying the same model A and indoor context supports a narrowly conditioned statement

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

Required output fields

Order	Field	How to complete
1	Original claim	Use the supplied source, calculation, or explicit unknown
2	Evidence source and location	Use the supplied source, calculation, or explicit unknown
3	Applicable audience, version and conditions	Use the supplied source, calculation, or explicit unknown
4	Supported scope	Use the supplied source, calculation, or explicit unknown
5	Unsupported or contradicted portion	Use the supplied source, calculation, or explicit unknown
6	Publishable revision	Use the supplied source, calculation, or explicit unknown
7	Supported, pending or withdrawn	Use the supplied source, calculation, or explicit unknown
8	Revision and recheck conditions	Use the supplied source, calculation, or explicit unknown

Verification cases

MK-005-C05 | The specification is true, but no industry comparison data is available

Expected: Functional benefits may be proposed; do not claim the product is unique or number one

MK-005-C06 | The information consists only of technical terms

Expected: Explain their role under the known usage conditions first; do not invent unverified effects

Method sources

Source file: Meta廣告學程 101 讓AI幫你投出廣告

Location: USP

Source basis: extracted from course materials

Source URL: https://docs.google.com/presentation/d/19GaScd4rGE8V4iqPfemeK8-QAwbSIeOKGpB5OwwTMlo/edit

English translation of source excerpt:

Help identify the product's USP (Unique Selling Proposition). This is also your first opportunity to communicate with the AI. It is good if it identifies the point, but if it does not get what you mean, make sure to tell it your thinking

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

assets/check-context.py15 KB
assets/context-contract.json17 KB

Frequently asked questions

What does the Mk 005 AI skill do?

Selling-point evidence matching. Use when the task requires a claim, evidence, and gap comparison table. Apply this method to the specified inputs and verify the deliverable

Why use Mk 005 on TypingMind?

Because you install it once and use it with any model. Mk 005 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 005 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/backtrue/thinkwithblack-skill/tree/main/en/skills/mk-005. 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 005?

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 005?

As many as you like. As long as a model supports skills, you can use Mk 005 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mk 005 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

Land And Deploy

garrytan

CommunityPopular

Land and deploy workflow. (gstack)

Clawsweeper

Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions…

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

MK-005 | Selling-point evidence matching

Purpose

Required inputs

Method Steps

Calculation and Interpretation

Required output fields

Verification cases

Method sources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now