RadarTopicsBuildersWeeklyReads
Open Source Radar
Leonxlnx/

taste-skill

GitHubWebsite

Taste Skill provides portable agent design and image-generation skills for AI-powered frontend interfaces. It offers multiple installable skills with adjustable design controls and anti-slop rules, plus image-to-code workflows.

72kstars
4.9kforks
53issues
MITlicense
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 4, 2026

What it is

Taste Skill provides portable Agent Skills to improve AI-built frontend interfaces, including layout, typography, motion, spacing, and image-generation references for boards. It supports integrating with ChatGPT Images and other generators, then passing results to coding agents.

How it works

The repository contains multiple skills under the taste-skill family. The Skills table lists install names and descriptions, such as design-taste-frontend for the default v2 experimental skill, design-taste-frontend-v1 for the original behavior, and other specialized skills (e.g., gpt-taste, image-to-code, redesign-existing-projects, brandkit, imagegen-frontend-web/mobile). The README explains that Skills output either code or reference images depending on the skill.

Getting started

Install via the CLI as shown:

npx skills add https://github.com/Leonxlnx/taste-skill

Install a single skill by its install name:

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend"

To upgrade from v1 to v2:

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend"

For pinning v1 explicitly:

npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend-v1"

Recent releases

The repository shows no releases listed under Latest (0). The README indicates a v2 experimental default with ongoing development.

Traction

Star history badge indicates activity over time. Current stars: 71680; forks: 4927; open_issues: 53.

License

MIT. The project states MIT License in the License section.

Agent skills inside · 13
All skills →
stitch-design-tasteSemantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.Frontendredesign-existing-projectsUpgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.Frontendindustrial-brutalist-uiRaw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.Data & Analyticsgpt-tasteElite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.Frontendimage-to-codeElite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.FrontendbrandkitPremium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.Security
SharePost on XLinkedIn
All trending reposRevenue-verified startups →