Taste Brand Identity logo

Taste Brand Identity

Community
madebymustafa
taste-brand-identity

Brand identity generation for agents: logo mark concepting, wordmark typography, lockups, clear space and minimum sizes, color application, favicon and og-image construction, and the one-page brand sheet. Use when asked to create a logo, identity, or brand assets for a product or site. Stack on the design-taste core skill.

Overview

Publishermadebymustafa
Repositorydesign-taste
Skill nametaste-brand-identity
Stars
198
Forks
10
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 madebymustafa on GitHub. Read the source before you install it.

Installation

Install the Taste Brand Identity 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/madebymustafa/design-taste/tree/main/skills/taste-brand-identity
  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/madebymustafa/design-taste.git /tmp/design-taste
mkdir -p .claude/skills
cp -r /tmp/design-taste/skills/taste-brand-identity .claude/skills/taste-brand-identity
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Taste Brand Identity 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 Taste Brand Identity 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 Taste Brand Identity 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.

taste-brand-identity

A logo is a memory aid, not a drawing. This skill makes sure the identity survives a favicon and a billboard.

1. THE CONCEPT (Before Any Drawing)

  1. One idea, two words: the mark reduces to a single association ("north + needle", "record + flower"). If you can't say it in two words, the concept isn't there yet.
  2. Literal is the last resort: a generic icon of the product category (spark, rocket, chat bubble, gear) is what every other mark does. Reach for the abstract idea behind the product.
  3. Test at 16px before loving it: the mark must read as a favicon first. If the concept needs 3 colors or fine detail to live, it fails the test.
  4. Two colors, hard ceiling: one ink + one accent (or monochrome). A mark that needs its gradient to exist is not a mark.

2. WORDMARK TYPOGRAPHY (The Half Nobody Checks)

  • Prefer modifying a strong existing face over inventing a font: letterspacing (−0.03em), case, a punctuation detail (. in "skittie.dev"), or one cutout/glyph swap.
  • One typographic move per wordmark: track tight OR case change OR a single altered glyph. Two moves = a novelty logo.
  • Test the wordmark in: caps, sentence case, and at 12px. If it doesn't survive small, tighten or accept a secondary lockup.
  • Never letterspace lowercase (it breaks the word shape). Never stretch type (use the real condensed family).

3. THE LOCKUP (Mark + Wordmark, Formalized)

  • Build on a construction grid: mark and wordmark on shared optical centers, clear space = height of the mark's smallest element (or 1/4 the mark width) on all sides.
  • Three lockups, defined once: horizontal (mark + wordmark), stacked (mark above wordmark), compact (mark + short wordmark, for small spaces).
  • Minimum sizes: mark ≥ 16px (favicon), ≥ 24px (in-app), ≥ 12px wordmark in compact lockups only.
  • Banned lockup crimes: shadowed marks, gradient marks, outlined marks at small sizes, mark alone without the brand name on the first view.

4. COLOR APPLICATION

  • The identity lives in ink + one accent (from the palette the page uses). A reversed (light-on-dark) variant is required — define both.
  • Accent distribution: the accent is a signal (links, one button, active states, the logo's accent detail) — never a background fill.
  • Provide a "monochrome only" fallback: every brand asset exists in 100% ink as a default.
  • If the logo is a wordmark, its color rule is: same ink as headings — never a rainbow of per-section colors.

5. THE DELIVERABLE SET (Ship All of These)

  1. Primary lockup — SVG, currentColor-compatible.
  2. Favicon — 32px and 180px (apple-touch): the mark alone, centered, its own square tile.
  3. og-image — 1200×630 canvas: mark or wordmark top-left or centered, one accent detail, clear space ≥ 80px margins; this is the most-viewed brand asset on the internet — never let it be a screenshot of the site.
  4. One-page brand sheet — mark, wordmark, clear space diagram, min sizes, palette (with tokens), type pair, do/don't rows. This becomes the agent's own brand guideline file.

6. DO / DON'T (The Fast Filter)

DoDon't
Simplify until one element remainsAdd a stroke, shadow, and gradient "for depth"
Test at 16px, 48px, 400pxDesign only at 400px and pray
One typographic moveCustom-draw letters that fight the font
Provide the reversed variantShip only the version that works on white
Make the og-image deliberatelyLet socials crop a screenshot

7. CHECKLIST (Fail the Identity If…)

  • The concept can't be stated in two words.
  • More than two colors (plus neutrals).
  • Any gradient, shadow, or outline needed for legibility.
  • The mark at 16px is ambiguous with the competition's.
  • No reversed variant exists.
  • No clear-space/min-size rule defined.
  • The og-image is missing or is a page screenshot.

Frequently asked questions

What does the Taste Brand Identity AI skill do?

Brand identity generation for agents: logo mark concepting, wordmark typography, lockups, clear space and minimum sizes, color application, favicon and og-image construction, and the one-page brand sheet. Use when asked to create a logo, identity, or brand assets for a product or site. Stack on the design-taste core skill.

Why use Taste Brand Identity on TypingMind?

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

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

Which AI models can use Taste Brand Identity?

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 Taste Brand Identity?

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

Is the Taste Brand Identity AI skill free?

Yes. It is published on GitHub by madebymustafa 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 👇