A visual editing workflow for building React user-interface components from screenshots. React is a tool for creating web interfaces, and the workflow shows the reference image beside a live preview while you make changes.

Use it to recreate or refine a React component such as a login form from one or more desktop or mobile screenshots. It requires the SDD command-line tool and a Playwright browser connection.

It makes visual differences easier to spot than reviewing code alone. You can compare the component with the screenshot while developing it.

sdd-ui — Skill for Claude Code and Codex by sifter-ai: A visual editing workflow for building React user-interface components…

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.

agentmods

npx agentmods add skills/sifter-ai/sifter/sdd-ui

Any agent

npx skills add sifter-ai/sifter --skill sdd-ui

Clone the repo

git clone --depth 1 https://github.com/sifter-ai/sifter

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-ui.svg)](https://agentmods.dev/skills/sifter-ai/sifter/sdd-ui)

Your own site

<a href="https://agentmods.dev/skills/sifter-ai/sifter/sdd-ui"><img src="https://agentmods.dev/badge/skills/sifter-ai/sifter/sdd-ui.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 891 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00035	$0.00891
Opus 5	$0.00017	$0.00445
Sonnet 5	$0.00007	$0.00178
Haiku 4.5	$0.00003	$0.00089

Measured 5d ago against content hash b0032a9fee00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-ui 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 5d 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.

.agents/skills/sdd-ui/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD UI — Visual Component Editor

Purpose

Use this workflow when implementing a React component from a screenshot reference in an SDD project. The split-panel editor shows the spec screenshot on the left and the live component on the right, so you can iterate visually until they match.

Prerequisites

sdd CLI installed globally
Playwright MCP configured in Claude Code settings
- e.g. @playwright/mcp or @executeautomation/playwright-mcp
- If not configured, inform the user and stop — visual feedback won't work without it

Workflow

Step 1 — Read the spec

Read the SDD feature file to understand what the component should look like and do. Look for any screenshot paths referenced in the feature doc.

Step 2 — Launch the editor

# Single screenshot — detached (recommended when run by an agent)
sdd ui launch-editor LoginForm \
  --screenshot product/features/auth/login.png \
  --detach

# Multiple screenshots (e.g. desktop + mobile)
sdd ui launch-editor LoginForm \
  --screenshot product/features/auth/login-desktop.png \
  --screenshot product/features/auth/login-mobile.png \
  --detach

The command will:

Scaffold code/components/LoginForm.tsx if it doesn't exist
Print the exact component file path to edit
Start the editor at http://localhost:5174

With --detach the process runs in background and the terminal is immediately free. Without --detach it runs in foreground (use Ctrl+C to stop).

With multiple screenshots, the left panel shows a tab per screenshot. With a single screenshot, no tab bar is shown.

Step 3 — Implement the component

Edit the file printed by sdd ui launch-editor (e.g. code/components/LoginForm.tsx).

Write a React component that matches the screenshot. Use standard HTML/CSS or inline styles — no external UI library unless the project already uses one.

Vite HMR will update the right panel automatically on every save.

Step 4 — Visual check with Playwright

After each save, screenshot the live preview and compare it with the spec:

Read the full file on GitHub · 114 lines

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.

5d ago First seen · 114 lines · 35 tokens per session scan A b0032a9fee00

Subscribe to this mod's changes

sdd-ui is a skill published in the GitHub repository sifter-ai/sifter (55 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 891 once invoked, about $0.0002 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.

Design and UX Frontend React

v8-jit

V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches, megamorphic deopt, closure…

vercel/next.js · 88 tokens

react-patterns

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

affaan-m/ECC · 49 tokens

e2e-write-visual-test

Use when writing a Playwright visual regression (screenshot comparison) test, tagging a test @visual, generating or updating baseline screenshots, running visual tests locally, or debugging a failing screenshot comparison in CI.

payloadcms/payload · 50 tokens

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

verify

Use when you want to validate changes before committing, or when you need to check all React contribution requirements.

react/react · 23 tokens