frontend-taste

frontend-taste is a skill for Claude Code from fatihkan/badi. It costs 0 tokens per session (982 once invoked), scanned A, original, MIT.

A set of frontend design rules for building polished interfaces with deliberate typography, colour, layout, and motion choices.

In plain words
What is it for?
Use it for landing pages, app interfaces, redesigns, and other frontend work where visual hierarchy and animation matter.
Why use it?
It helps prevent default-looking web pages by making the coding agent follow a chosen visual direction instead of making generic design decisions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it for landing pages, app interfaces, redesigns, and other frontend work where visual hierarchy and animation matter.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fatihkan/badi/frontend-taste
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add fatihkan/badi --skill frontend-taste
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for frontend-taste

README.md
[![agentmods](https://agentmods.dev/badge/skills/fatihkan/badi/frontend-taste/github.svg)](https://agentmods.dev/skills/fatihkan/badi/frontend-taste)
Your own site
<a href="https://agentmods.dev/skills/fatihkan/badi/frontend-taste"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/frontend-taste/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for frontend-taste

Your own site · 80×15
<a href="https://agentmods.dev/skills/fatihkan/badi/frontend-taste"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/frontend-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 982 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00982
Opus 5 $0.00000 $0.00491
Sonnet 5 $0.00000 $0.00196
Haiku 4.5 $0.00000 $0.00098

Measured 3d ago against content hash d16d171e0cad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

frontend-taste scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills-vault/frontend-taste/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontend Taste Skills

Bundled collection of 9 frontend design skills. Each enforces a different visual direction and works with Claude Code / any LLM-based coding agent.

How to Use

Invoke by describing the visual direction in your prompt. Claude Code auto-routes based on keywords:

  • "premium landing page" / "high-agency frontend" -> default
  • "strict layout, GSAP motion, editorial" -> gpt-taste
  • "Notion/Linear style, editorial, minimal" -> minimalist
  • "Swiss typography, raw, brutalist" -> brutalist
  • "calm, expensive, polished" -> soft
  • "redesign this existing app" -> redesign
  • "give me the full code, no placeholders" -> output
  • "generate a DESIGN.md for Google Stitch" -> stitch
  • "generate design images first, then implement" -> images-first

You can also explicitly load one variant:

Use the "frontend-taste/brutalist" skill to redesign the header.

The 9 Variants

Variant When to use
default/ (design-taste-frontend) Safest general pick. Premium frontend with controllable DESIGN_VARIANCE / MOTION_INTENSITY / VISUAL_DENSITY dials.
gpt-taste/ Stricter, more opinionated. Python-driven layout randomization, AIDA page structure, wide editorial typography, mandatory GSAP ScrollTriggers. Best for GPT/Codex models.
minimalist/ (minimalist-ui) Clean editorial interfaces. Warm monochrome, flat bento grids, muted pastels. No gradients, no heavy shadows.
brutalist/ (industrial-brutalist-ui) Swiss typographic print + military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color.
soft/ (high-end-visual-design) High-end agency feel. Exact fonts, spacing, shadows, card structures. Blocks common defaults that make AI designs look cheap.
redesign/ (redesign-existing-projects) Audits current UI, identifies generic AI patterns, applies high-end standards without breaking functionality.
output/ (full-output-enforcement) Overrides LLM truncation. Bans placeholder patterns. Handles token-limit splits cleanly. Pair with any visual skill.
stitch/ (stitch-design-taste) Generates agent-friendly DESIGN.md files for Google Stitch.
images-first/ (image-taste-frontend) Image-first workflow: generate reference images, analyze them deeply, then implement. For visually-led projects.

Read the full file on GitHub · 71 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 71 lines · 0 tokens per session scan A d16d171e0cad

Subscribe to this mod's changes

frontend-taste is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 982 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.

Related

Other skills, from other repositories

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

AvinashP/AgentsAtlas · 64 tokens

heroui

Build accessible UIs using HeroUI v3 components (React + Tailwind CSS v4 + React Aria). Use when creating React interfaces, selecting UI components, implementing forms, navigation, overlays, or data display. Use when installing HeroUI v3, customizing themes, accessing component documentation, building with compound…

ruchernchong/claude-kit · 121 tokens

apple-design

Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…

samuelpatro/.claude · 80 tokens

frontend-ui-ux

Designer-turned-developer expertise for crafting stunning UI/UX even without design mockups.

shahidshabbir-se/my-pi-setup · 22 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

AvinashP/AgentsAtlas · 77 tokens

landing-page-generator

Generate complete, deploy-ready landing pages from any repository. Use when creating a homepage for an open-source project, building a project website, converting a README into a marketing page, or standardizing landing pages across multiple repos.

FlorianBruniaux/claude-code-plugins · 48 tokens