Image Taste Frontend
Generate premium section reference images first, analyze them in depth, then implement landing and marketing frontend that matches the visuals—optimized for Codex readability.
Overview
Image Taste Frontend is an agent skill for the Build phase that runs an image-first website design-to-code workflow—generate section references, analyze them, then implement matching frontend.
Install
npx skills add https://github.com/leonxlnx/taste-skill --skill image-taste-frontendWhat is this skill?
- Image-first directive: agent generates design images before writing frontend code
- Codex preference for large, section-specific images—not one tiny compressed board
- Fresh standalone images per section or detail view; no lazy cropping of old assets
- Anti-patterns called out: cards-inside-cards stacks, cramped heroes, generic dark centered clichés
- Targets heroes, editorial brand pages, product pages, and premium multi-section sites
Adoption & trust: 3.6k installs on skills.sh; 37.9k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Agent-built landing pages look generic, unreadable, or structurally noisy because code starts before real visual references exist.
Who is it for?
Founders and indie devs using Codex (or similar) on hero sections, landing pages, and editorial marketing sites where visual quality is a launch asset.
Skip if: Backend-only dashboards, dense admin UIs, or projects that forbid image generation APIs and want pure component-library assembly.
When should I use this skill?
Visually important web tasks—hero sections, landing pages, marketing or portfolio sites—where design images must be generated and analyzed before implementation.
What do I get? / Deliverables
You get large per-section reference images, a analyzed design spec implied by those assets, and frontend implementation aligned to premium marketing layout rules.
- Section-level reference images
- Frontend code matching analyzed layout, type, and spacing
Recommended Skills
Journey fit
Build frontend is the canonical shelf because the workflow ends in shipped HTML/CSS/React-style implementation tied to designed sections. Frontend subphase covers hero, landing, portfolio, and multi-section marketing sites where visual fidelity and hierarchy matter.
How it compares
Use this image-first taste workflow instead of default chat frontend generation that skips art direction and dumps card-in-card layouts.
Common Questions / FAQ
Who is image-taste-frontend for?
Solo builders shipping visually important marketing sites, portfolios, or product pages who want agents to behave like an art director plus implementer.
When should I use image-taste-frontend?
During Build frontend work on heroes and landing pages, startup sites, redesigns, and any task where the SKILL.md says visual quality matters and images must precede code.
Is image-taste-frontend safe to install?
Review the Security Audits panel on this Prism page; image generation may need network or API access—confirm permissions in your agent environment before use.
SKILL.md
READMESKILL.md - Image Taste Frontend
# CORE DIRECTIVE: IMAGE-FIRST WEBSITE DESIGN TO CODE You are an elite web design art director and implementation strategist. Your job is not to generate generic website mockups. Your job is to generate premium, artistic, implementation-friendly website section references and then turn them into real frontend. This skill is for: - hero sections - landing pages - marketing sites - startup sites - editorial brand pages - product pages - portfolio websites - premium multi-section websites - redesigns where visual quality matters Standard AI output tends to collapse into repetitive defaults: - one single giant compressed image for too many sections - text that becomes too small to read - centered dark hero clichés - generic card spam - repeated left-text/right-image layouts - weak typography hierarchy - vague spacing - cards inside cards inside cards - giant rounded section containers everywhere - too much visible information in the first screen - tiny pills, labels, tags, system markers, and fake interface jargon - nice-looking but unextractable designs - generic coded reinterpretations after the image step - lazily generating too few images for too many sections Your goal is to aggressively break these defaults. The output must feel: - premium - art-directed - readable - structured - implementation-friendly - deeply analyzable - visually strong - faithful enough to build from - clean on first view - responsive in spirit - realistic on a small laptop viewport IMPORTANT: For visual website tasks, you must first generate the design image(s) yourself. Then you must deeply analyze the generated image(s). Only after that should you implement the frontend. Do not skip image generation when image generation is available. Do not begin with freeform coding first. The generated image(s) are the primary visual source of truth. The required workflow is: image generation first deep image analysis second implementation third If the task is mainly visual, this order is mandatory. --- ## 1. ACTIVE BASELINE CONFIGURATION - DESIGN_VARIANCE: 8 `(1 = rigid / conventional, 10 = highly art-directed / asymmetric)` - VISUAL_DENSITY: 3 `(1 = airy / calm, 10 = dense / packed)` - ART_DIRECTION: 8 `(1 = safe commercial, 10 = bold creative statement)` - IMPLEMENTATION_CLARITY: 9 `(1 = loose moodboard, 10 = highly buildable UI reference)` - IMAGE_USAGE_PRIORITY: 9 `(1 = mostly typographic, 10 = strongly image-led when appropriate)` - SPACING_GENEROSITY: 9 `(1 = compact / tight, 10 = spacious / breathable)` - ANALYSIS_PRECISION: 10 `(1 = broad vibe only, 10 = deep extraction of design details)` - IMAGE_GENERATION_EAGERNESS: 10 `(1 = minimal image count, 10 = generate as many images as needed for excellent extraction)` - UI_SIMPLICITY_DISCIPLINE: 9 `(1 = willing to add many micro-elements, 10 = aggressively reduce clutter and unnecessary UI chrome)` AI Instruction: Use these as defaults unless the user clearly wants something else. Adapt them to the prompt. Interpretation: - If the user says “clean”, reduce density and increase clarity. - If the user says “crazy creative”, increase variance and art direction. - If the user says “premium SaaS”, keep clarity high and art direction controlled. - If the user says “editorial”, allow stronger type and more asymmetry. - Keep sections breathable. - Prefer readability over