image-to-frontend

image-to-frontend is a skill for Claude Code from JairoTorregrosa/jaiskills. It costs 125 tokens per session (1,560 once invoked), scanned A, original, MIT.

A workflow for turning a product brief or reference image into a working React or HTML web page. React is a tool for building web interfaces from reusable code components.

In plain words
What is it for?
Use it to create landing pages, app screens, dashboards, marketplaces, personal sites, and other interfaces from a brief or screenshot.
Why use it?
It helps translate visual ideas into a design direction and then into frontend code, while accounting for the difficulty of matching complex reference images closely.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the jaiskills plugin — 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to create landing pages, app screens, dashboards, marketplaces, personal sites, and other interfaces from a brief or screenshot.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jairotorregrosa/jaiskills/image-to-frontend
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 JairoTorregrosa/jaiskills --skill image-to-frontend
Clone the repo
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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-to-frontend

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/image-to-frontend"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/image-to-frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,560 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 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 $0.00125 $0.01560
Opus 5 $0.00063 $0.00780
Sonnet 5 $0.00025 $0.00312
Haiku 4.5 $0.00013 $0.00156

Measured 12d ago against content hash 0e5568298ffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

image-to-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 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.

skills/openai/image-to-frontend/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image → Frontend (gpt-image via askcodex)

End-to-end workflow: brief → 4 visual variants → chosen variant → detailed build spec → real frontend code → iterate to pixel-close. Powered by the askcodex CLI (askcodex image create / askcodex image edit) from the askcodex repo. No API key needed — askcodex reuses the credentials codex login already stored.

GI2 is genuinely strong: photorealistic web/mobile app screenshots, accurate text rendering, world knowledge, identity preservation across edits. But ~3 in 4 attempts fail to closely replicate a complex reference without strategy. Follow the steps; do not shortcut.

Step 1 — Brief

Collect from the user (or draft and confirm):

  • Business / product name and one-line pitch
  • Audience and tone (expert + grounded? playful? minimal?)
  • Primary CTAs (book a call, sign up, try demo)
  • Aesthetic preferences, palette, vibe references
  • Type (SaaS dashboard, marketplace landing, personal site, mobile app, infographic)
  • Existing brand assets, icons, color tokens (paths)

Ambiguity is fine in step 2 — it surfaces options. Explicit direction massively improves variant quality.

Step 2 — Generate 4 stylistic variants

Fire 4 askcodex image create commands in parallel (background Bash calls in one message), each with a distinct visual direction (e.g. editorial-serif, bento grid, glass-morphism, brutalist-mono). Same brief, different style. Save to mockups/v1.pngmockups/v4.png.

Use the prompt template in examples/variant-prompt.md as the quoted prompt: askcodex image create "<prompt>" -o mockups/v1.png. Verify outputs with file mockups/v*.png. Read each PNG with the Read tool to view, then show the variants to the user.

Step 3 — Image → detailed build spec

Once the user picks a variant, do not jump straight to "build it." Generate a meticulous build spec from the chosen image. Pass the PNG to a strong code/vision model and ask it to enumerate:

Read the full file on GitHub · 90 lines

Files

What ships with it

6 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. 12d ago First seen · 90 lines · 125 tokens per session scan A 0e5568298ffa

Subscribe to this mod's changes

image-to-frontend is a skill published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 11d ago), licensed MIT. It adds 125 tokens to every session and 1,560 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 2026-08-31.

Related

Other skills, from other repositories

design-system

DaisyUI + Tailwind CDN design system spec. Preloaded into design-related agents and referenced by design skills.

pcatattacks/solopreneur-plugin · 26 tokens

eval-graphics

Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright. For producing the charts in a published eval/data study.

elvisun/newsjack · 47 tokens

shadcn-ui

Provides complete shadcn/ui component library patterns including installation, configuration, and implementation of accessible React components. Use when setting up shadcn/ui, installing components, building forms with React Hook Form and Zod, customizing themes with Tailwind CSS, or implementing UI patterns like…

giuseppe-trisciuoglio/developer-kit · 74 tokens

tailwind-design-system

Skill for creating and managing a Design System using Tailwind CSS and shadcn/ui. Use when defining design tokens, setting up theming with CSS variables, building a consistent UI component library, initializing a design system configuration, or wrapping shadcn/ui components into design system primitives.

giuseppe-trisciuoglio/developer-kit · 62 tokens

tailwind-css-patterns

Provides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling React/Vue/Svelte components, building responsive layouts, implementing design systems, or optimizing CSS workflow.

giuseppe-trisciuoglio/developer-kit · 62 tokens

loom-accessibility

Web accessibility patterns, WCAG compliance, and inclusive design.

cosmix/loom · 16 tokens