Brand Intake logo

Brand Intake

Community
charlie947
brand-intake

The setup step every other skill in this pack reads. A short interview plus 3 to 5 reference frames becomes two files in your project, brand.md (who you are, what you sell, your assets) and MOTION.md (your colours, type, timing and motion rules), plus a rule in CLAUDE.md so Claude reads them before it animates anything. Use at the start of any motion project, or when someone says "set up my brand", "brand intake", "build my motion design system", "make it look like my brand", "onboard me", "write my MOTION.md" or drops a batch of brand frames into chat.

Overview

Publishercharlie947
Repositorymotion-graphics-skills
Skill namebrand-intake
Stars
428
Forks
62
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by charlie947 on GitHub. Read the source before you install it.

Installation

Install the Brand Intake 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/charlie947/motion-graphics-skills/tree/main/skills/brand-intake
  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/charlie947/motion-graphics-skills.git /tmp/motion-graphics-skills
mkdir -p .claude/skills
cp -r /tmp/motion-graphics-skills/skills/brand-intake .claude/skills/brand-intake
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Intake 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 Brand Intake 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 Brand Intake 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.

Brand intake

Every other skill in this pack reads the two files this one writes. Without them, Claude picks its own colours, its own type and its own idea of motion. Run this once per brand.

Start straight away

When someone asks for this, your first message is the Batch 1 questions. No summary of the skill, no preamble.

Step 1: The interview, in two batches

Batch 1. Ask these four together, then wait:

  1. What is the brand called, and what do you do, in one line?
  2. Who is it for? One sentence on the person watching.
  3. What do you sell or promote in your videos? The offer, the product or the newsletter, with its real link.
  4. What should people feel in the first second? Pick up to three: calm, premium, playful, urgent, technical, warm, bold.

Batch 2. Then ask these three, and wait: 5. Your colours as hex codes, your font names, and your logo files (SVG or PNG, attached). No hex codes? Say "sample them from my site" and give the link. 6. 3 to 5 reference frames: screenshots of motion you already like, from Dribbble, Pinterest or your own work. Put them in a folder called examples. 7. One thing your motion must never do.

If an answer is blank, ask for it once more, then move on. Never fill a gap with a guess.

Step 2: Write brand.md

Save it in the project root, under 300 words:

# Brand

## Name and what we do
## Audience
## What we promote (with the real link)
## The feeling
## Assets
Colours (hex, typed by me or sampled from a named source), fonts, logo file names
## Never

Step 3: Write MOTION.md from the frames

Read every frame in examples, then write MOTION.md with this brief to yourself:

Write one file called MOTION.md that any AI can read before it animates anything for me. It must cover:

1. Every colour as a hex code, and what each one is for
2. The fonts and the type sizes
3. Timing: how things come in, how long they hold, and how they leave
4. How things move: the frame rate, the easing, and anything that makes it feel handmade
5. Texture and finish
6. Five things my motion must never do, named plainly
7. One example, described shot by shot, of it done right

Work only from what is in the frames. Where you cannot tell, write ASK ME rather than guessing.

Show the user the file before you save it. Colours in brand.md win over colours sampled from a frame.

Step 4: Add the read-first rule to CLAUDE.md

Create CLAUDE.md if it does not exist, and add this block word for word:

Before designing, generating or animating anything, read MOTION.md in full.

Every colour, font, timing and motion value comes from that file.

The file sets the look, not the ambition. When I say go all out, go all out.

If something I ask for is not covered there, ask me rather than choosing for yourself.

When you have finished, check your own frames against MOTION.md, fix what fails, and only then show me.

What I learned the hard way

  • Mixed frames give mixed looks. My five frames held four different looks. The file named all four and asked which to use. Pick one master look, or name which look goes with which job.
  • The ambition line is not optional. Without "the file sets the look, not the ambition", my first try with the file came out far too polite.
  • ASK ME is a feature. With the file in place, the one-line prompt stopped and asked a question before building. That is the file working.
  • Sampled hex codes drift. A colour read off a JPEG is a few points out. Use the hex codes you typed wherever they exist.

Step 5: Prove it (optional, two minutes)

Run the same one-line prompt twice, once in an empty folder and once in this project: "Make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are. Go all out." Put the two side by side. Both should go all out. Only one should look like yours.

Hand off

Tell the user brand.md, MOTION.md and the CLAUDE.md rule are in place, then list what to try next: launch-video, vox-explainer, animated-chart, milestone-reveal. Until both files exist, no other skill may call its result on-brand.

Frequently asked questions

What does the Brand Intake AI skill do?

The setup step every other skill in this pack reads. A short interview plus 3 to 5 reference frames becomes two files in your project, brand.md (who you are, what you sell, your assets) and MOTION.md (your colours, type, timing and motion rules), plus a rule in CLAUDE.md so Claude reads them before it animates anything. Use at the start of any motion project, or when someone says "set up my brand", "brand intake", "build my motion design system", "make it look like my brand", "onboard me", "write my MOTION.md" or drops a batch of brand frames into chat.

Why use Brand Intake on TypingMind?

Because you install it once and use it with any model. Brand Intake 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 Brand Intake in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/motion-graphics-skills/tree/main/skills/brand-intake. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Brand Intake?

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 Brand Intake?

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

Is the Brand Intake AI skill free?

Yes. It is published on GitHub by charlie947 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 👇