The easiest way to get Taste Skill results: download TasteCode. Its design agent briefs, builds and visually reviews your UI. Source on GitHub.
Sponsors
 |
Sidrune AI: one API for GPT, Claude, and other leading AI models. Sign up through this link and get $3 in API credit. |
|
interfaces.dev · A design engineering magazine by Jakub Krehel |
|
React Bits · animated React components for creative interfaces |
 |
IMG.LY · CreativeEditor SDK |
 |
Sent.dm · messaging APIs for SMS, WhatsApp, and RCS |
Taste Skill is a set of Agent Skills that make coding agents design websites instead of assembling the average landing page. The default skill gives the agent an art direction, real pictures and a way to check its own work in a real browser.
Pages it has built, each from one brief:
 |
 |
 |
 |
The photographs are real, found in open archives and credited by the skill (credits). Watch the launch film.
Install · How it works · Skills · FAQ · Sponsors · License
Install
npx skills add https://github.com/Leonxlnx/taste-skill
That installs every skill in this repo with the npx skills CLI. To install one, pass its install name:
npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend"The default skill runs its scripts with Node 22+ and an installed Chrome, Edge or Chromium. It installs nothing and needs no API keys. Finding pictures needs network access.
Claude Code plugin
Run these inside Claude Code. Every skill is namespaced under taste-skill:, so they do not collide with your other skills.
/plugin marketplace add Leonxlnx/taste-skill
/plugin install taste-skill@taste-skill
/plugin update upgrades it later.
Codex plugin
codex plugin marketplace add Leonxlnx/taste-skill codex plugin add taste-skill@taste-skill
Start a new Codex session afterwards so the skills are loaded.
From a clone, linked instead of copied
./install.sh symlinks the skills into Claude Code (--codex for Codex, --all-agents for both), so a git pull updates them in place. ./install.sh --list shows every install name.
Already have the skill? Run the install command again. The install name did not change, and the older versions stay available under their own names (see Skills).
How v2 works
The default skill is built from a study of 247 curated sites. A build runs in six steps:
- Reads the brief and lists what only this client has.
- A script deals three of 20 researched directions and the agent picks one.
- Finds the idea: one sentence tying the client's own material to that direction.
- Builds with real pictures and footage from open collections, credited.
- Checks the page in a real browser at three widths and fails it on slop.
- Looks at its own screenshots and fixes the top three problems, up to three rounds.
A build takes roughly 30 to 45 minutes and a few hundred thousand tokens. Details are in the changelog and the study.
Skills
Each skill does one job. You do not need all of them. The install name is the value you pass to --skill.
| Skill | Install name | What it does |
|---|---|---|
| taste-skill | design-taste-frontend |
v2. Art direction for landing pages, marketing sites, portfolios and product pages, in any stack. Works as described above. |
Skills for a specific job (8)
| Skill | Install name | What it does |
|---|---|---|
| redesign-skill | redesign-existing-projects |
Existing projects: audit the UI first, then fix layout, spacing, hierarchy and styling. |
| image-to-code-skill | image-to-code |
Generate site references, analyse them, then build the frontend to match. |
| gpt-tasteskill | gpt-taste |
A stricter variant for GPT and Codex: more layout variance, stronger motion direction. |
| soft-skill | high-end-visual-design |
Calm, polished UI: soft contrast, whitespace, spring motion. |
| minimalist-skill | minimalist-ui |
Editorial product UI with a restrained palette and crisp structure. |
| brutalist-skill | industrial-brutalist-ui |
Hard mechanical language: Swiss type, sharp contrast, experimental layout. |
| stitch-skill | stitch-design-taste |
Rules for Google Stitch, with an optional DESIGN.md export. |
| output-skill | full-output-enforcement |
For when the model ships half-finished work: full output, no placeholder comments. |
Image generation skills (3)
These produce design images only, no code. Use them with ChatGPT Images, Codex image mode or any agent that generates images, then hand the frames to your coding agent.
| Skill | Install name | What it does |
|---|---|---|
| imagegen-frontend-web | imagegen-frontend-web |
Website comps: hero, landing page, multi-section. |
| imagegen-frontend-mobile | imagegen-frontend-mobile |
Mobile screens and flows for iOS, Android and cross-platform. |
| brandkit | brandkit |
Brand-kit boards: logo directions, palettes, type, applications. |
Which one should I use?
- Building a new public page: taste-skill.
- Improving a page that already exists: redesign-skill.
- The visual direction is already decided: soft-skill, minimalist-skill or brutalist-skill.
- You want images first, then code: an image-generation skill, or image-to-code-skill for the whole pipeline in one go.
- The agent keeps cutting its output short: add output-skill.
Older versions of taste-skill
Kept for projects that depend on their exact behaviour.
| Skill | Install name | What it is |
|---|---|---|
| taste-skill-v2-experimental | design-taste-frontend-v2-experimental |
The single-file, dial-driven rewrite that was the default before v2. |
| taste-skill-v1 | design-taste-frontend-v1 |
The original. |
npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend-v2-experimental" npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend-v1"
Both have three 1 to 10 dials at the top of the file: DESIGN_VARIANCE (centred and clean to asymmetric), MOTION_INTENSITY (hover only to scroll-driven) and VISUAL_DENSITY (spacious to dense). v2 has no dials. Its direction comes from the draw and its limits from the inspector.
Common Questions
What does the default skill need?
Node 22 or newer and Chrome, Edge or Chromium. It installs nothing and uses no API keys. It needs the internet only to find pictures.
Where do the pictures come from, and can I use them?
From open collections such as Wikimedia Commons, Openverse and the Met. Only public domain, CC0, CC BY and CC BY-SA files are offered, and the skill puts the credits on the page. Replace them with your own when you have them.
Does it work with React, Vue, Svelte, plain HTML?
Yes. The rules are about design, not a framework.
Is it for dashboards and app screens?
No. The default skill is for public-facing pages. Use minimalist-skill or soft-skill for product UI.
Support the project
If Taste Skill helps you, consider sponsoring:
Open Source Supporters
 |
Get a Kimi API key: taste-skill users get 10% bonus API credits on their first purchase. |
 |
 |
Community sponsors
Feedback: open an issue or pull request, DM @lexnlin or @blueemi99, or email hello@tasteskill.dev.
Taste Skill has no official token, coin, or crypto project. Any token using my name, image, or project is unaffiliated and not endorsed by me.
License
MIT License · Copyright (c) 2026 Leonxlnx