Frontend

Organization

OyadotAI

frontend

Use when building or changing anything in the frontend: a page, a component, a layout, styling, copy on screen. Produces distinctive, production-grade UI that fits this project's existing design, covers every state, is accessible, and is checked in a browser before it is called done.

Overview

Publisher	OyadotAI
Repository	`oya-browser`
Skill name	`frontend`
Stars	351
Forks	281
Bundled files	Instructions only
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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by OyadotAI on GitHub. Read the source before you install it.

Installation

Install the 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/OyadotAI/oya-browser/tree/main/.agents/skills/frontend
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/OyadotAI/oya-browser.git /tmp/oya-browser
mkdir -p .claude/skills
cp -r /tmp/oya-browser/.agents/skills/frontend .claude/skills/frontend

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

Use it in TypingMind

Enable 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 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 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.

Frontend

Build interfaces that look designed for this product, work in every state, and are verified by looking at them.

1. Read before drawing

Find the project's design system before inventing one: tokens (CSS variables, Tailwind config, theme file), the component library, how an existing page of the same kind is built. Grep for the pattern you are about to write; reuse it. Two ways to draw a button is one too many.
Read the repository instructions (CLAUDE.md or AGENTS.md) for who the users are. A dashboard for engineers wants density; a landing page wants one idea per screen.

2. Commit to a direction

When there is no system yet, or the ask is a new surface, choose a clear aesthetic direction and execute it with precision — refined minimalism and bold maximalism both work; intentionality is the point. Never the generic AI look:

choose typography for the product; preserve established app fonts and use native system fonts where appropriate; introduce a display face only when the content benefits from one
no purple-to-blue gradient on white, no evenly spread timid palette: one dominant colour, sharp accents, and colour reserved for meaning
no card grid because it is the default; compose for the content — asymmetry, overlap, generous space or deliberate density
colours, spacing, radii and type sizes are tokens (CSS variables), never literals scattered through components

3. Every state, not the happy one

For each surface, design and build: empty, loading, partial, error (with what to do next), permission denied, offline or stale, and far more data than expected (long names, 10,000 rows). A blank area with no reason is a bug. Skeletons match the final layout so nothing jumps.

4. Accessible by default

Semantic elements first (button, a, label, nav, headings in order). Everything works from the keyboard with visible focus. Text contrast at least 4.5:1 in light and dark. Images have alt text; icon-only buttons have labels. Honour prefers-reduced-motion and prefers-color-scheme.

5. Motion and performance

Motion carries information — an arrival, a change, a relationship — or it goes. Prefer CSS transitions; animate transform and opacity only. Nothing animates between a person and the thing they are waiting for. Images are sized and lazy below the fold; fonts are subset and font-display: swap; no layout shift when data lands.

6. Responsive

Check the supported minimum width and a comfortable desktop width with no accidental horizontal scroll. For responsive websites, check 375, 768 and 1440px. Use at least 44px touch targets on touch interfaces; keep desktop controls consistent with the existing application.

7. Look at it

Read the oya-browser skill and use Oya Browser exclusively. If Oya is unavailable, report the blocker without substituting another browser or harness. Run the dev server and open the page in an owned Oya tab. Take a screenshot at each width and in each theme and look at it; read the console for errors and warnings. Check the empty and error states by forcing them. A UI change is not done until you have seen it render — the type checker cannot see a button that is white on white.

Report

Say which direction you chose and why, the states you built, what you verified by looking (with the widths and themes), and anything you could not check.

Frequently asked questions

What does the Frontend AI skill do?

Why use Frontend on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OyadotAI/oya-browser/tree/main/.agents/skills/frontend. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use 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 Frontend?

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

Is the Frontend AI skill free?

It is published on GitHub by OyadotAI. 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

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Frontend

1. Read before drawing

2. Commit to a direction

3. Every state, not the happy one

4. Accessible by default

5. Motion and performance

6. Responsive

7. Look at it

Report

Frequently asked questions

Related AI Skills

Set up your own AI workspace now