Brand Assets logo

Brand Assets

Community
roslove44
brand-assets

Generates or regenerates a project's brand assets (logo, favicon and their variants) through the brand toolchain, faithfully. Use when the user wants to "regenerate the logo / the favicon", "add an icon or logo variant", "a new brand variant", or "set up a project's brand toolchain". Works in tools/<project>/ reusing brand-artisan/brandkit, outputs to out/<project>/brand/ and then gets promoted to brands/<project>/. Requires a project with its brand.md in place.

Overview

Publisherroslove44
Repositorybrand-artisan
Skill namebrand-assets
Stars
5
Forks
0
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 roslove44 on GitHub. Read the source before you install it.

Installation

Install the Brand Assets 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/roslove44/brand-artisan/tree/main/skills/brand-assets
  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/roslove44/brand-artisan.git /tmp/brand-artisan
mkdir -p .claude/skills
cp -r /tmp/brand-artisan/skills/brand-assets .claude/skills/brand-assets
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Assets 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 Assets 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 Assets 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-assets: generating brand assets

Goal: produce or evolve a project's brand files (logo, favicon, icons, OAuth variants and so on) with the brand toolchain, faithfully to what already exists. This is a separate world from the TS/Satori engine: here you produce the files that brands/<project>/logo and /favicon contain; the engine consumes them through brand().

Env and commands: see tools/README.md. This skill does not duplicate the launch commands (npx tsx tools/…). It encodes how to do it well.

0. Prerequisites (blocking)

  • Resolve <project>. Check brands/<project>/brand.md (colors, geometry, rules). Missing guidelines -> STOP: /new-project <project> first.

1. Frame it

Three cases:

  • Regenerate an existing asset (the guidelines or the geometry changed).
  • Add a variant of an existing asset (new color, background, size, e.g. the oauth-120-* files).
  • Start a new brand (create tools/<project>/, see the appendix).

2. The discipline of faithful reproduction (the heart of it)

Never guess the geometry of an existing asset. Inspect it first. For each reference file, read off the palette:

bash
npx brand-artisan colors brands/<project>/logo/logo.png

It gives the dimensions and the palette sorted by pixel count: the first block is the background (transparent? opaque white?), the following ones the inks and accents. For an element's scale and margins, boundingBox(decode(file)) from brand-artisan/colors returns the box of what is painted ({ x, y, width, height }, or null if everything is transparent). Don't hand-write a pixel walk: the function is there and it is tested.

A real example (the OAuth variants): the palette revealed that mark-white was blue arcs on a white background (not white arcs), and the bounding box gave the exact scale of the bracket-O inside the frame. That is what keeps a visual from being "roughly right".

3. Build

In tools/<project>/ (never anywhere else):

  • Reuse brand-artisan/brandkit for the generic plumbing:
    • renderSvg(svg, { width } | { height }, background?): SVG -> PNG,
    • renderPixels(svg, size): the same pixels as RGBA, for the checks,
    • makeIco(images): multi-resolution .ico,
    • loadInstanced(font, axes): access to the glyphs (outline, advance, bbox).
  • Keep local (in the brand's own script) the colors, the geometry (paths, viewBox) and the layout, never in brandkit.ts.
  • If some new generic plumbing would serve every brand, add it to brandkit.ts (and update tools/README.md in mirror).
  • The output goes to out/<project>/brand/ through the script's OUT constant. Don't write directly into brands/ (see §5).

4. Validate

Compare every regenerated file (in out/<project>/brand/) with its reference (in brands/<project>/): dimensions, bounding box and palette must match (slight edge antialiasing differences are acceptable; a difference in color, size or framing is not). Also run the built-in pixel validation where it exists (the favicon prints a 32 px check).

5. Promote

out/<project>/brand/ is ephemeral (the out/ folder is gitignored). After a visual review and validation, copy the approved files into brands/<project>/logo/ or /favicon/, then update brand.md if the list of variants changes (placement, new variants).

Success criterion: the regenerated assets are faithful (dimensions, bounding box and palette conform), produced by a script that reuses brandkit.ts, and promoted into brands/<project>/ with an up-to-date brand.md.

Appendix: starting a new brand

  1. Create tools/<project>/; take inspiration from tools/calame/ (build-logo.ts, build-favicon.ts).
  2. Drop the source font in it if needed (e.g. _geist.ttf).
  3. Import the foundation: import { … } from "brand-artisan/brandkit". Colors and geometry come from brand.md, never invented.
  4. OUT -> out/<project>/brand/. Check, validate, promote.

Frequently asked questions

What does the Brand Assets AI skill do?

Generates or regenerates a project's brand assets (logo, favicon and their variants) through the brand toolchain, faithfully. Use when the user wants to "regenerate the logo / the favicon", "add an icon or logo variant", "a new brand variant", or "set up a project's brand toolchain". Works in tools/<project>/ reusing brand-artisan/brandkit, outputs to out/<project>/brand/ and then gets promoted to brands/<project>/. Requires a project with its brand.md in place.

Why use Brand Assets on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/roslove44/brand-artisan/tree/main/skills/brand-assets. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Brand Assets?

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 Assets?

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

Is the Brand Assets AI skill free?

Yes. It is published on GitHub by roslove44 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 👇