content / skill
Taste Skill
Apply design rules for layout, typography, motion and spacing to the frontends your AI coding agent builds.
At a glance
- Purpose
- Apply design rules for layout, typography, motion and spacing to the frontends your AI coding agent builds.
- Runs in
- Chat app with skills, Local agent with shell
- Operating systems
- Not stated
- Needs
- Runtime: Not stated; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
- Tool type
- Skill
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- According to the README, the skills are portable across Codex, Cursor and Claude Code, and are framework agnostic, with React, Vue and Svelte named as working. You can also paste a SKILL.md into ChatGPT or Codex conversations. The Stitch skill follows Google Stitch-compatible rules. The image-generation skills pair with ChatGPT Images or similar generators.
- External costs
- The repository is MIT-licensed and states no pricing. Your coding agent, image generator or model provider may charge for usage.
- Permissions
- The skills act through your coding agent with the access you give it. According to the README, they are instruction files that guide design and code output, and the image-generation skills produce reference images only. The README does not describe file, shell, network or credential access.
- Usage terms
- MIT License, as stated in the repository. See its LICENSE file for the exact terms.
Code on GitHub
Leonxlnx/taste-skill
MITTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Topics: agent ai claude claude-code codex coding design frontend
Public GitHub data fetched · 0 days old
Skill folders in this repository (13)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
Taste Skill is a set of portable agent skills for frontend design. According to the README, the skills aim to upgrade AI-built interfaces with stronger layout, typography, motion and spacing instead of boilerplate-looking interfaces. Each skill does one job, and the README says you do not need all of them at once.The main skill, taste-skill, installs as design-taste-frontend. The README describes version 2 as an experimental rewrite that reads the brief, infers a design language and tunes three dials: design variance, motion intensity and visual density. Other skills include the preserved version 1, a stricter variant for GPT and Codex, a redesign skill for existing projects, style skills (soft, minimalist and brutalist), a skill that enforces full output, a Google Stitch skill and an image-to-code skill.
Three image-generation skills (imagegen-frontend-web, imagegen-frontend-mobile and brandkit) produce reference images only. The README says to use them with ChatGPT Images, Codex image mode or another image generator, then hand the results to a coding agent.
Who it is for
Developers and designers who build frontends with an AI coding agent and want design rules applied to its output.Example tasks
Build a frontend with the taste-skill and adjust its variance, motion and density dials.Audit an existing UI and fix layout, spacing and hierarchy with the redesign skill.
Generate website or mobile reference images with the imagegen skills, then implement them in code.
Add the output skill when an agent keeps truncating its work.
Create brand-kit boards with logo directions, palettes and type using the brandkit skill.