LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Skill

Taste Skill (dont minimalist-ui)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

Collection of "anti-slop" skills for front-end work: bans purple gradients, Inter everywhere, and rows of rounded cards; variants include minimalist-ui, etc.

The best antidote to the "AI-generated" look; choose a single variant per project rather than installing everything at once.

Overall score
8.7 /10
Security: nothing to flag
Utility
7.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

AI agents often produce interfaces that all look alike: purple gradients, Inter font applied everywhere, heavily rounded card corners, and generic animations. Taste Skill is a collection of rule files (SKILL.md) designed to correct these default reflexes and push the agent toward more considered visual choices.

In practice, you install one or more skills via an npx command, and the rule file is read by the agent (Claude Code, Cursor, Codex, Gemini CLI, v0, Lovable, and others) before it generates front-end code. The default skill (v2, experimental) reads the project context, infers the appropriate visual direction, then applies strict rules on typography, spacing, motion, and density. Three numeric dials (DESIGN_VARIANCE, MOTION_INTENSITY, VISUAL_DENSITY, from 1 to 10) let you adjust the output without changing the underlying rules.

Taste Skill is aimed at developers and teams who use AI agents to build interfaces and want to avoid a generic look. Specialised skills cover specific cases: auditing existing projects (redesign-skill), minimalist editorial direction (minimalist-skill), brutalist aesthetics (brutalist-skill), generating reference images (imagegen-frontend-web, mobile, brandkit), and Google Stitch compatibility (stitch-skill).

Taste Skill is not a component library or code package: it generates nothing on its own and only works if the tool being used supports SKILL.md files. People who do not use an AI agent for coding will get no direct benefit from it.

What it offers

  • ·Default v2 skill (experimental): reads the project context, infers the visual direction, and applies a strict ruleset before any code is generated.
  • ·Three adjustment dials (DESIGN_VARIANCE, MOTION_INTENSITY, VISUAL_DENSITY) to tune the level of layout experimentation, animation depth, and information density.
  • ·Specialised skills by visual direction: minimalist (minimalist-skill), brutalist (brutalist-skill), premium and calm (soft-skill).
  • ·Audit skill for existing projects (redesign-skill): analyses the current interface before proposing fixes to layout, spacing, and hierarchy.
  • ·Image-generation skills (imagegen-frontend-web, imagegen-frontend-mobile, brandkit) to produce design references before handing off to a coding agent.
  • ·output-skill to force the agent to deliver complete code with no placeholder comments or truncated sections.
  • ·Compatible with many agents: Claude Code, Cursor, Codex, Gemini CLI, v0, Lovable, OpenCode, AI Studio.
  • ·Single-skill installation available via the --skill flag, without installing the entire collection at once.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
GitHub, skills.sh
Host
claude-code
Licence
MIT
Other hosts
claude-code, cursor, codex, gemini-cli
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active
Last release
24 October 2026

Links and repository checked on 25 October 2026 · added on 23 September 2026

How to install Taste Skill (dont minimalist-ui)

1. Make sure Node.js is installed on your machine (required for npx). 2. In your terminal, at the root of your project, run: npx skills add https://github.com/Leonxlnx/taste-skill 3. To install a single skill, add the --skill flag followed by the install name, for example: npx skills add https://github.com/Leonxlnx/taste-skill --skill "minimalist-ui" 4. Confirm that the SKILL.md file has been added to your project before launching the agent. 5. You can also manually copy any SKILL.md file into your project or paste it directly into a conversation with your agent.
npx skills add https://github.com/Leonxlnx/taste-skill

Official documentation ↗

In the same category

Whole category Design & slides →