Aesthetic logo

Aesthetic

Community
amanmaqsood
aesthetic

Redesign and implement complete, polished websites in an existing or greenfield codebase. Use for an explicit website or codebase implementation request such as "make this site aesthetic," "design this better," "give this website a premium UI," or "polish and build this website"; use design-with-ai for advice, examples, critique, or direction without implementation.

Overview

Publisheramanmaqsood
Repositorydesign-with-ai
Skill nameaesthetic
Stars
7
Forks
0
Bundled files
4
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.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Aesthetic 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/amanmaqsood/design-with-ai/tree/main/plugins/design-with-ai/skills/aesthetic
  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/amanmaqsood/design-with-ai.git /tmp/design-with-ai
mkdir -p .claude/skills
cp -r /tmp/design-with-ai/plugins/design-with-ai/skills/aesthetic .claude/skills/aesthetic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aesthetic 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 Aesthetic 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 Aesthetic 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.

Aesthetic

Leave the user with working website code, not a moodboard or a list of suggestions. Build a coherent client-specific interface, use outside components only when they fit, and verify the rendered result.

Protect the product

  • Preserve working business logic, factual copy, supplied assets, analytics, and framework choices unless the user explicitly puts them in scope.
  • In an existing project, adapt to its framework, styling system, component conventions, and package manager. Do not add React, Tailwind, or shadcn solely to reach a component catalog.
  • For greenfield interactive product sites, prefer current Next.js, TypeScript, and Tailwind when no simpler stack fits better. Choose the least complex stack that satisfies the brief.
  • Treat deployment, paid services, authenticated MCP setup, and framework replacement as separate approval points. If code or a design asset sourced by the agent has unclear license or reuse rights, do not use it; choose a clearly permitted source instead. A user-supplied asset may be used within the requested project, but record it as Provided by client and make no broader rights claim.

Run the build

Read references/build-workflow.md, then:

  1. Inspect the repository, run its baseline checks, and identify the routes and states in scope.
  2. Derive a visual direction from the client, content, product, and existing brand signals. State the direction briefly and proceed unless a missing brand decision would lead to materially different results.
  3. Inventory existing primitives before adding anything. If a gap remains, read references/component-sources.md and verify the current official source, compatibility, access, and license.
  4. Implement foundations and shared components before page-level polish. Preserve behavior while improving hierarchy, typography, spacing, color roles, density, responsiveness, states, and purposeful motion.
  5. Read references/visual-qa.md, run the site, inspect it at representative desktop and mobile sizes, exercise important states, and run the project's build and tests.
  6. Report the files changed, outside components used, checks run, rendered views inspected, and anything that remains unverified.

Keep the system coherent

Use one component foundation and at most two accent sources. More sources require a concrete gap that the current system cannot solve. Adapt imported components to the same tokens and interaction rules; remove demo branding, dead variants, and unnecessary dependencies.

Create or update UI-SOURCES.md when external component code, fonts, icons, images, templates, or hosted design assets enter the client project. Record the official URL, retrieval date, verified license or terms, install or copy method, local destination or runtime use, and meaningful modifications. Mark user-supplied assets as Provided by client when no public source exists; do not invent a license. Preserve required notices.

Motion must explain change, maintain spatial context, or provide useful feedback. Keep frequent and keyboard-driven actions immediate, support reduced motion, and remove effects that hurt responsiveness or clarity.

Use agents when useful

When the host supports parallel agents, divide bounded work into source research, non-overlapping implementation lanes, and an independent visual QA pass. Do not let agents edit the same files concurrently. Use the same workflow sequentially when subagents are unavailable; completion does not depend on a particular orchestration feature.

Do not overclaim

A successful build proves that the project compiles. It does not prove that the website looks good or works through the whole journey. If rendered inspection is unavailable, finish safe code and build checks, then state that visual QA is incomplete.

Bundled files

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

Frequently asked questions

What does the Aesthetic AI skill do?

Redesign and implement complete, polished websites in an existing or greenfield codebase. Use for an explicit website or codebase implementation request such as "make this site aesthetic," "design this better," "give this website a premium UI," or "polish and build this website"; use design-with-ai for advice, examples, critique, or direction without implementation.

Why use Aesthetic on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/amanmaqsood/design-with-ai/tree/main/plugins/design-with-ai/skills/aesthetic. 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 Aesthetic?

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 Aesthetic?

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

Is the Aesthetic AI skill free?

Yes. It is published on GitHub by amanmaqsood 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 👇