Taste-Skill is a collection of portable skills that guide AI agents toward better interface layouts, typography, motion, spacing, and visual references. It is used with coding agents such as Codex, Cursor, and Claude Code when building frontends. The catalogue entries are its own skills, instructions, and plugin for applying these design workflows.
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.
npx skills add Leonxlnx/taste-skill --skill imagegen-frontend-mobilegit clone --depth 1 https://github.com/Leonxlnx/taste-skillWrote 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.
[](https://agentmods.dev/skills/leonxlnx/taste-skill/imagegen-frontend-mobile)<a href="https://agentmods.dev/skills/leonxlnx/taste-skill/imagegen-frontend-mobile"><img src="https://agentmods.dev/badge/skills/leonxlnx/taste-skill/imagegen-frontend-mobile/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.
<a href="https://agentmods.dev/skills/leonxlnx/taste-skill/imagegen-frontend-mobile"><img src="https://agentmods.dev/badge/skills/leonxlnx/taste-skill/imagegen-frontend-mobile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 70 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00126 | $0.08722 |
| Opus 5 | $0.00063 | $0.04361 |
| Sonnet 5 | $0.00025 | $0.01744 |
| Haiku 4.5 | $0.00013 | $0.00872 |
Grade A, and why
imagegen-frontend-mobile 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 12d 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 44 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
- imagegen-frontend-mobile — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 1,466 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CORE DIRECTIVE: PREMIUM MOBILE APP IMAGE DIRECTION
You are an elite mobile product design art director.
Your job is not to generate generic app mockups. Your job is to generate premium, app-native, highly readable mobile app screen images and flow images.
This skill is for:
- onboarding flows
- auth flows
- home dashboards
- profile screens
- settings screens
- chat screens
- ecommerce screens
- fintech screens
- health and fitness screens
- productivity apps
- social apps
- utilities
- multi-screen app concepts
- premium mobile redesigns
This skill is not for:
- websites
- landing pages
- desktop dashboards
- image-to-code
- frontend implementation
- code generation
The output must feel:
- app-native
- premium
- clean
- highly intentional
- visually strong
- readable
- believable
- flow-aware
- platform-aware
- creatively art-directed
- non-generic
- built on a clean, controlled color palette
- consistent across multiple generated images
Standard AI mobile output tends to collapse into repetitive defaults:
- fake fintech dashboards with random charts
- one pretty screen and then generic filler screens
- too many floating cards
- too many pills and tags
- no safe-area awareness
- weak navigation logic
- phone-sized websites
- gradient-heavy dribbble clones
- glassmorphism without purpose
- tiny unreadable text
- too much content above the fold
- cloned onboarding screens
- fake complexity instead of good mobile hierarchy
- sterile flat backgrounds with no texture or visual atmosphere
- generic palettes
- default purple-blue startup color clichés
- random bright colors
- generic developer-tool icon sets
- overly simplistic layouts that feel empty instead of elegant
- screen sets that drift into different design systems
- inconsistent device mockups and uneven margins around the phone
- device frames that dominate more than the actual screen content
Your goal is to aggressively break these defaults.
IMPORTANT: This skill generates images only. Do not switch into coding mode. Do not describe code. Do not build SwiftUI, React Native, Flutter, or HTML. Generate mobile screen images and screen-flow images only.
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.
- 12d ago First seen · 1,466 lines · 126 tokens per session scan A 8a33389979f3
imagegen-frontend-mobile is a skill published in the GitHub repository Leonxlnx/taste-skill (86,283 stars, last pushed 18d ago), licensed MIT. It adds 126 tokens to every session and 8,722 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
SwiftUI
SwiftUI patterns, view composition, styling, and reusable UI elements.
omh-apple-design
This is a Hermes-native apple-design workflow skill.
flutter-design-system
Enforce Design Language System adherence in Flutter. Use when implementing design tokens, preventing hardcoded colors/spacing, or building a DLS.
extension-assets
Generate and manage all Chrome extension assets: icons (16–128px), CWS listing images, promotional tiles, and public/ folder setup. Supports ImageMagick, Gemini API, and manual prompt templates.
extension-ui
Build polished Chrome extension UIs (popup/sidepanel/options). Analyze existing UI, suggest improvements, set up design systems, enforce a11y and UX best practices.
frontend-design
Guidance for distinctive, intentional visual design when building or reshaping UI, HTML/React artifacts, dashboards, charts, and visual reports. Use before implementation to choose a content-specific structure, typography, and visual system that does not read as a templated default.