AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPICE simulation, download datasheets, source components, and prep boards for fabrication.

Open Pencil: a public semi-auto design workflow for Pencil users, design review, layout iteration, and visual production handoff.

UxNote is a lightweight annotation bar for mockups and websites—drop one script to highlight, pin, and export feedback directly in the browser.

Visual-first architecture workspace with typed graphs, deterministic validation, semantic diffs, and proposal-gated AI changes.

Three LLMs review your design plan in parallel — paste 30 lines into your CLAUDE.md, no install needed.

A navigator for system and human design — structure-first, question-driven, reasoning-safe

ESP for AI Coding — Agent skills on the philosophy on software design, grounded in decades of engineering experience.

UIMax MCP — Turns Claude Code into a frontend expert that reviews and fixes your UI automatically. Free for Pro plan users.

Visual design diffs in GitHub PRs. Before/after screenshots for every .pen design change. Free, open-source GitHub Action.

Second Opinion is a pre-mortem review tool that helps engineering teams identify potential failure modes.

AI-powered UX audits — MIT-licensed snapshot of the commercial project, archived May 2026. Vite/React + Supabase + Figma plugin.

Claude Code plugin for Google Antigravity CLI (agy) — modern replacement for gemini-cli (deprecated 18 Jun 2026). 7 slash commands: web research with citations, browser walkthrough .webm recording, structured URL scraping, PDF/docx/image to Markdown, UX design review, code rescue, health check.

Structured, phase-gated architecture design powered by Claude Code. Enforces decision gates, challenges assumptions, and produces documented architecture decisions.

面向建筑行业知识工作从业者与 AI 研发团队的 Skills、Workflow 与多 Agent 工具包 / Building-industry AI agent skills for BIM, IFC, RAG, GraphRAG, project evidence work, code review, and runtime governance.

A taste system for AI agents. 288 skills, 80 agents, 12 rules, and 8 hooks that turn generic AI output into work with genuine design quality. Anti-slop detection, typography craft, color systems, brand voice, product strategy, and 50+ specialized reviewers across UI, industry, platform, and content domains.

AI-powered design review, UX analysis, SEO audit, content generation, DevOps & testing toolkit for Claude Code. 12 skills, 12 parallel subagents. One-liner install.

Annotate the UI of your running web app. AI agents apply the changes back to source. Dev-only Vite + Webpack plugin with MCP, CLI, and HTTP surfaces.

The design intelligence runtime for AI agents. 49 rules. Zero LLM. MCP-native. Give your agent eyes.

A Claude Code skill that runs a 6-persona architecture review panel on your design docs..

Claude skill: scored UI/UX audits and silent prevention of the failures AI ships. 15 categories, severity rubric, durable-fix recommendations.