design-qa

Uiprobe plugin for Claude Code: a check Claude can run against your Figma design. It compares the built page with the frame, value by value, and Claude fixes the differences.

AI screenshot comparison platform for signage and cross-platform QA

Visual QA CLI for AI-built frontends that renders pages, finds design and accessibility issues, and writes agent-ready fix prompts.

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.

Compare Figma designs with rendered UIs using Playwright. Visual regression and structured reports for CI and experimental AI repair loops.

8 agent skills for real Figma files, for Claude Code, Codex, Copilot CLI and Gemini CLI: 90 Plugin API gotchas, checks before and after every write, a handoff gate.

Two composable Claude Code skills for design-to-code fidelity: extract exact specs from Figma, then verify the running web or mobile app matches them.

Visual QA CLI for AI-built frontends that renders pages, finds design and accessibility issues, and writes agent-ready fix prompts.

Design DNA Phase 3 verification harness — scores fidelity (tokens, style, effects) and drives a correction loop until ship-ready.

Spacing & grid QA for AI-generated UIs, in the agent loop. MCP server that audits computed geometry and returns fix hints.

Figma-style inspection for any website — type styles, spacing, and element measurement, right in Chrome

Evidence-first UI alignment audit skill for AI coding agents (Claude Code / Cursor / Codex): real rendered evidence, typed findings, interactive A/B acceptance — without touching product code.

macOS screenshot tool for designers collaborating with AI: annotate a region, write the fix, hand over an image plus a numbered instruction list.

Free Chrome extension for website annotation, UI review and visual bug reporting. Mark up screenshots with numbered notes and send feedback to Jira, Figma, Google Docs, Word or PDF.

An AI-agent skill for sourcing UI components and animations legally — a dated license audit of 20+ libraries (Magic UI, Aceternity, React Bits…) — plus motion specs, icon strategy, design-QA checklists and build workflows.

A four-agent Claude Code workflow for UX analysis, Figma-ready design planning, independent design QA, and human-approved handoffs. Read-only by default.

Audit Figma flows for missing states, broken transitions, unsafe recovery paths, and unresolved product decisions.

Structured style-fidelity checker for design-to-code: diff Figma vs. front-end per-attribute + by geometric boundary distance. AI judges only what needs judgment — a faster, cheaper, quantifiable alternative to screenshot visual diff.

MCP server + CLI for AI-powered design fidelity — compare Figma designs or screenshots against rendered UI. 90% mutation recall, zero false positives on a golden eval set. No API keys — uses your Claude Code or Codex subscription.

视觉设计实验室 / Visual Design Lab：面向职业视觉设计的 AI 原生、平台中立、宿主原生设计智能与生产能力层。闭环为 Brief→Reference→Direction→Design System→宿主原生产物→读回→证据→回滚，含质量门、rights 与生产预检。不替代 Photoshop/Figma/Blender，不做第二画布或通用 Agent runtime。能力分级 E0–E5，静态 Adapter 只证 E1；实况以仓内生成状态为准。