platform: Skill for Claude Code

.agents/skills/image-taste-frontend/SKILL.md

image-taste-frontend is a skill for Claude Code, Codex from tutur3u/platform. It costs 23 tokens per session (358 once invoked), scanned A, a copy of image-to-code, Apache-2.0.

A design-to-code guide for visually important websites that starts with generated design images and then turns them into frontend code. It covers heroes, landing pages, marketing sites, product pages, portfolios, and redesigns.

In plain words
What is it for?
Use it when planning or implementing premium website sections, especially hero areas and multi-section pages where image composition, typography, spacing, and asset choice matter.
Why use it?
It helps avoid generic layouts, unreadable text, oversized single images, repeated card patterns, and designs that are difficult to build accurately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is tutur3u/platform's own configuration. It tells Claude Code and Codex how to work on platform itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything platform configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tutur3u/platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tutur3u/platform/main/.agents/skills/image-taste-frontend/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tutur3u/platform

Made for: Claude Code, Codex.

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 image-taste-frontend

README.md
[![agentmods](https://agentmods.dev/badge/skills/tutur3u/platform/image-taste-frontend/github.svg)](https://agentmods.dev/skills/tutur3u/platform/image-taste-frontend)
Your own site
<a href="https://agentmods.dev/skills/tutur3u/platform/image-taste-frontend"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/image-taste-frontend/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 image-taste-frontend

Your own site · 80×15
<a href="https://agentmods.dev/skills/tutur3u/platform/image-taste-frontend"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/image-taste-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 358 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.
Origin 100% copy Near-identical to another mod 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 $0.00023 $0.00358
Opus 5 $0.00012 $0.00179
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00002 $0.00036

Measured 3d ago against content hash 246b5ebe0957, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

image-taste-frontend 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.

Origin

This is a copy

100% identical to image-to-code — 1,245 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/image-taste-frontend/SKILL.md · 40 lines

What it actually says

Image-Guided Frontend Design

Use supplied references as the starting point when the user provides them. Generate a concept when a visual reference would materially resolve an open design decision or the user asks for image-first exploration. Small UI edits and established layouts usually need direct implementation, not a fresh set of mockups.

Reference Selection

Choose the smallest useful reference set. A page overview can establish hierarchy; a separate section or detail image helps when the overview is too compressed to inspect. Add or regenerate images to resolve specific uncertainties, not to satisfy a quota. Use the available image tool according to its editing and generation rules. Do not substitute generated concepts for factual product screenshots.

Inspect And Implement

Inspect the reference before translating it. Extract layout proportions, content hierarchy, typography, spacing, palette, controls, and image treatment. Separate intentional design choices from generation artifacts such as garbled text or impossible interactions. Use real copy and semantic, accessible components.

Preserve supplied brand assets and project conventions. Match the important visual relationships while adapting responsively; a bitmap cannot specify every viewport or interaction. Keep the hero legible on a small laptop, avoid unnecessary nested containers, and keep primary actions discoverable.

Verification

Compare the implementation with its reference at relevant desktop and mobile sizes. Fix observable differences that matter to hierarchy and usability. Verify keyboard access, contrast, overflow, loading/error states, and reduced motion where relevant. Continue through the requested implementation and fixes. If image or browser tools are unavailable, report the limitation and complete the work that remains possible.

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 Changed · -1,189 lines · -95 tokens per session 246b5ebe0957
  2. 10d ago First seen · 1,229 lines · 118 tokens per session scan A b3de60152b20

Subscribe to this mod's changes

image-taste-frontend is a skill published in the GitHub repository tutur3u/platform (53 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 358 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to image-to-code, differing in 1,245 lines, and is treated as a copy.

Related

Other skills, from other repositories

magic-ui

Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projects. It covers component selection, shadcn registry installation (@magicui/), integration patterns, and practical quality checks for accessibility and maintainability.

magicuidesign/magicui · 56 tokens

frontend-engineer

!cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/input-validation.md 2>/dev/null || true !cat skills/shared/protocols/tool-efficiency.md 2>/dev/null || true !cat .production-grade.yaml 2>/dev/null || echo "No config — using defaults" !cat .forgewright/codebase-context.md…

buiphucminhtam/forgewright · 55 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…

shadcn-ui/ui · 94 tokens

migrate-radix-to-base

Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.

shadcn-ui/ui · 61 tokens

nextjs-app-router

Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.

trpc/trpc · 74 tokens

nextjs-pages-router

Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.

trpc/trpc · 67 tokens