Design Taste Frontend

Community

cgallic

design-taste-frontend

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Overview

Publisher	cgallic
Repository	`kai-cmo-harness`
Skill name	`design-taste-frontend`
Stars	61
Forks	8
Bundled files	2
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 cgallic on GitHub. Read the source before you install it.

Installation

Install the Design Taste Frontend 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/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/design-taste-frontend
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/design-taste-frontend

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/cgallic/kai-cmo-harness.git /tmp/kai-cmo-harness
mkdir -p .claude/skills
cp -r /tmp/kai-cmo-harness/harness/skills-v2/design-taste-frontend .claude/skills/design-taste-frontend

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

Use it in TypingMind

Enable Design Taste Frontend 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 Design Taste Frontend 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 Design Taste Frontend 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.

design-taste-frontend (v2, goal-oriented)

Third-party skill (Leonxlnx/taste-skill, MIT; see UPSTREAM.md and LICENSE). The complete, unmodified rule set is references/taste-rules.md in this folder. This file states the goal and the binding constraints; every rule in the reference still applies.

Objective

Ship a landing page, portfolio or redesign that does not read as templated or AI-generated, built for the audience the brief implies, using the brand material that already exists.

Done when

A one-line design read (page kind, audience, vibe, design-system or aesthetic family) and the three dials (DESIGN_VARIANCE, MOTION_INTENSITY, VISUAL_DENSITY) are stated before any code, with reasons.
For a redesign, the audit in section 11 of references/taste-rules.md is written before any change: brand tokens, IA, content blocks, patterns to keep and retire, and the current dial reading.
The page is rendered and screenshotted at mobile and desktop widths, in light and dark mode, and every box in the Final Pre-Flight Check (section 14) is honestly ticked. A failed box means the work is not done.

Constraints

Zero em dashes or en dashes anywhere visible, including alt text and button labels.
One theme per page, one accent colour, and one documented corner-radius system.
Hero: headline of at most 2 lines on desktop, subtext of at most 20 words, CTA visible without scrolling, no more than 4 text elements, and top padding of 96px at most.
Eyebrow labels: at most one per three sections. No split headers, no three consecutive image-and-text splits, no layout family used twice, and no duplicate CTA intent.
Real images, from an image tool, supplied assets, then seeded placeholders. No div-built fake screenshots, no hand-drawn decorative SVG, and no pills or captions over photos.
No invented precise numbers, fake testimonials or placeholder brands. Copy is re-read and every broken or cute-but-wrong line is rewritten.
WCAG AA contrast on every button, form field, label and helper text. Honour prefers-reduced-motion above motion level 3. Use no window scroll listeners.
Official packages when the brief maps to a real design system (section 2), and one system per project.
Redesigns never silently change URLs, primary nav labels, form field names, the logo or legal copy.

Context

Full rules, dial tables, bans, block-library schema and install commands: references/taste-rules.md.
Out of scope: dashboards, data tables, multi-step forms, code editors and native apps (section 13). Say so, and apply only the marketing-page parts.

Escalate when

The design read genuinely diverges (for example, Linear-clean versus experimental). Ask exactly one question.
Redesign mode is unclear between preserve and overhaul. Ask once.
No image source is available. List the exact placements and sizes that need images instead of shipping a text-only page.

Bundled files

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

references/taste-rules.md85 KB
UPSTREAM.md1 KB

Frequently asked questions

What does the Design Taste Frontend AI skill do?

Why use Design Taste Frontend on TypingMind?

Because you install it once and use it with any model. Design Taste Frontend 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 Design Taste Frontend in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cgallic/kai-cmo-harness/tree/main/harness/skills-v2/design-taste-frontend. 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 Design Taste Frontend?

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 Design Taste Frontend?

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

Is the Design Taste Frontend AI skill free?

It is published on GitHub by cgallic. Check the repository for licensing terms. 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

Grilling

mattpocock

CommunityPopular

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Teach

Teach the user a new skill or concept, within this workspace.

Api Design

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Accessibility

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

design-taste-frontend (v2, goal-oriented)

Objective

Done when

Constraints

Context

Escalate when

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now