screenshot-to-page

screenshot-to-page is a skill for Claude Code from lukedj78/dev-flow. It costs 197 tokens per session (5,121 once invoked), scanned A, original, MIT.

A skill that turns a UI screenshot into a working page and route inside an existing web app. It follows the app's design rules and component library, such as shadcn, Base UI, MUI, or Coss.

In plain words
What is it for?
Creating reusable page components from a screenshot, matching layout and styling, and checking the result through repeated rendering, screenshots, and pixel comparison.
Why use it?
It reduces the manual work of rebuilding a page from a visual reference while keeping the result consistent with the existing project.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the dev-flow plugin — 47 skills shipped together

Good fit Creating reusable page components from a screenshot, matching layout and styling, and checking the result through repeated rendering, screenshots, and pixel comparison.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lukedj78/dev-flow/screenshot-to-page
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 lukedj78/dev-flow --skill screenshot-to-page
Clone the repo
git clone --depth 1 https://github.com/lukedj78/dev-flow

Made for: Claude Code.

Or install dev-flow, the plugin that ships this one along with the rest of its 47 skills.

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 screenshot-to-page

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukedj78/dev-flow/screenshot-to-page/github.svg)](https://agentmods.dev/skills/lukedj78/dev-flow/screenshot-to-page)
Your own site
<a href="https://agentmods.dev/skills/lukedj78/dev-flow/screenshot-to-page"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/screenshot-to-page/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 screenshot-to-page

Your own site · 80×15
<a href="https://agentmods.dev/skills/lukedj78/dev-flow/screenshot-to-page"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/screenshot-to-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 197 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,121 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 $0.00197 $0.05121
Opus 5 $0.00098 $0.02560
Sonnet 5 $0.00039 $0.01024
Haiku 4.5 $0.00020 $0.00512

Measured 9d ago against content hash d117b2bae345, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

screenshot-to-page 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/visual_diff.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

screenshot-to-page/SKILL.md · 263 lines

How it starts

The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.

screenshot-to-page — screenshot → working route

This skill takes one screenshot and one route-name from the user, and produces a working page in the existing scaffolded app. The route renders close to the visual reference, uses only components and tokens already defined by the project's design system, and is reachable in pnpm dev.

What this skill targets

Pixel-perfect on what's reproducible: layout, typography, color, spacing, radii, component states. The skill iterates render → screenshot → pixel-diff → fix until the visual delta is below threshold (default <2% off-tokens).

Placeholder, with explicit flag, on what isn't: photography, illustration, custom illustrations, brand-licensed imagery. These are static raster contents that no skill can synthesize from a screenshot alone.

Componentized aggressively: the skill detects repeated visual patterns in the screenshot (3 cards with the same structure, 4 nav links, a list of testimonials, ...) and extracts each pattern into a reusable component before writing JSX. The page file ends up short and readable; the heavy lifting is in components/<PageName>/.

What this skill is NOT

  • Not a Figma-to-code service. The input is a static raster, not a vector.
  • Not a layout designer — if the screenshot is ambiguous (e.g., two interpretations of a section break), ask the user.

When this skill applies

  • A <project-root>/ exists (phase >= scaffolded).
  • .workflow/screenshots/ contains at least one image.
  • A .workflow/DESIGN.md exists with valid tokens.
  • The user names a route to build (/, /pricing, /dashboard, etc.) or points at a specific screenshot.

Contract

This skill follows the dev-flow contract — see references/contracts.md. Key facts:

  • Reads <root>/.workflow/screenshots/<filename>, <root>/.workflow/DESIGN.md, <root>/.workflow/meta.json#stack.
  • Writes the route into the codebase at the project root, at the canonical path for the framework:
    • Next App Router: <project-root>/app/<route>/page.tsx
    • Vite + React: registers a route in <project-root>/src/router.tsx (or whatever the scaffold uses) plus a component file <project-root>/src/pages/<Route>.tsx.
    • Astro: <project-root>/src/pages/<route>.astro.
  • Sets phase = "page_generated" (only if current phase is earlier in the enum).

Read the full file on GitHub · 263 lines

Files

What ships with it

2 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. 9d ago First seen · 263 lines · 197 tokens per session scan A d117b2bae345

Subscribe to this mod's changes

screenshot-to-page is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed today), licensed MIT. It adds 197 tokens to every session and 5,121 once invoked, about $0.0010 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

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).…

bytedance/deer-flow · 77 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

bytedance/deer-flow · 44 tokens

tutti-ui-system

Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.

tutti-os/tutti · 46 tokens

mcp-host-styling-integration

Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.

a5c-ai/babysitter · 44 tokens

moai-design-tools

Design tool integration specialist covering Figma MCP, Pencil renderer, and Pencil-to-code export. Use when fetching design context from Figma, rendering Pencil designs, or exporting to React/Tailwind code.

modu-ai/moai-adk · 45 tokens

moai-domain-uiux

UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.

modu-ai/moai-adk · 49 tokens