By AgentsORG
Audits and fixes UI design quality—animation, typography, color, accessibility, anti-patterns—by reading DESIGN.md tokens, running structured code reviews, and applying targeted diffs. Supports a six-subagent workflow for motion auditing, AI-tell scanning, and opinionated project references.
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
Consume the project's DESIGN.md and thread its tokens through UI code (CSS, Tailwind, or design-system components).
Fork pov.md for installer taste, or append a one-liner to gotchas.md after a real agent failure.
Audit animation timing, easing, springs, and transitions — decide first whether motion should exist, then apply the motion cluster.
Run a UI code review on the current snippet — Before / After / Why table per review-format, scoped to review-checklist.
Six narrow-purpose subagents ship with this skill. Each is a single markdown file with YAML frontmatter (`name`, `description`, `tools`, `model`) and a system-prompt body — the standard format read by Claude Code, Cursor, Codex, and any harness that supports the [Claude Code subagent spec](https://docs.claude.com/en/docs/claude-code/sub-agents).
Load when the user is running an Agentation two-session workflow and you are the Session 2 (fix) side. Watches MCP annotations from the critique session, reads each annotation's selector + file path + critique, applies the fix in code, commits, and loops to the next. Use only when the agentation MCP server is connected.
Load when the user asks "does this look AI-generated?", wants a content-authenticity audit, asks to delete AI-default tells from a UI, or is reviewing marketing copy that feels generic. Specializes in the anti-patterns cluster — purple gradients, Inter-on-marketing, stock copy, generic icons, placeholder testimonials. Returns a deletion list.
Load when the user has a DESIGN.md file in their project (the Google Labs design-token format) and wants generated UI to consume its tokens. Reads DESIGN.md, normalizes the tokens, and produces TypeScript / CSS variables / a Tailwind config / a token-applied snippet that respects the design system. Use whenever you're producing UI in a project that ships a DESIGN.md.
Load when the user asks about animation timing, easing, springs, transitions, gestures, stagger, or "this feels janky / theatrical / hesitant". Specializes in the motion cluster plus Jakub Antalik's transitions.dev catalog. Returns either a Before | After | Why table (for code) or a one-page motion plan (for new animation work).
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
An agent skill that encodes design engineering — the invisible details that make UI feel right. Distills Emil Kowalski (animation), Benji Taylor (delight + Agentation), Jakub Antalik (transitions), James Frewin (guidelines), Vercel (web-interface rules), Ben DC (CSS conventions), Google Labs design.md (design-token format), lucide-animated (icon animation), DiceBear (avatars), and Index (Emil Kowalski & Glenn Carstens-Peters — design vocabulary) into one navigable skill graph.
Not a tutorial. Not a doc site. A working memory the agent loads when you're reviewing UI code, picking an easing curve, designing a component, or asking "why does this feel flat?"
The fastest path — one command, any agent:
npx skills add AgentsORG/design-engineering
This uses the skills.sh CLI to install into your detected agent (Claude Code, Cursor, Windsurf, Codex, Gemini, Cline, Aider, and 18+ others). The CLI prompts for scope (project vs. global) and method (symlink vs. copy).
Install the full plugin bundle — skill graph, six workflow subagents, and slash commands — in one step via vercel-labs/plugins:
npx plugins add AgentsORG/design-engineering
# Dry run — see skills, agents, and commands before installing
npx plugins discover AgentsORG/design-engineering
# List detected agent hosts on this machine
npx plugins targets
# Cursor only, skip confirmation
npx plugins add AgentsORG/design-engineering --target cursor -y
Restart your agent tools after install. Slash commands (when your host supports them) include /design-engineering:review-ui, /design-engineering:motion-audit, /design-engineering:scan-ai-tells, /design-engineering:agentation-fix, /design-engineering:apply-design-md, and /design-engineering:fork-pov.
The repo also ships agent-specific plugin manifests so you can install via each agent's native plugin system:
Claude Code — uses .claude-plugin/marketplace.json + .claude-plugin/plugin.json. Skills under skills/ auto-discover.
# Add as a marketplace
/plugin marketplace add AgentsORG/design-engineering
/plugin install design-engineering
# Or test locally
claude --plugin-dir .
Codex — uses .codex-plugin/plugin.json with the full interface block (default prompts, brand color, capabilities).
codex plugin marketplace add AgentsORG/design-engineering --sparse .codex-plugin --sparse skills
Cursor — uses .cursor-plugin/plugin.json. Install via the Cursor Marketplace or sideload locally.
Settings → Plugins → Load unpacked → point at this repo root
All three manifests share the same name, version, description, author, homepage, repository, and license so plugin identity stays consistent across hosts. The Codex manifest adds interface (default prompts, brand color, capabilities); the Cursor manifest adds displayName, publisher, tags, and a $schema URL. CI lints all four manifests for valid JSON and version-parity with SKILL.md on every PR.
Two tools that compound the value of this skill — install both:
# Obsidian — view + edit the skill graph in a real graph view
# https://obsidian.md → "Open folder as vault" → pick this repo
# Agentation — click-to-annotate design review in your localhost dev environment
npx skills add benjitaylor/agentation
Obsidian turns the wikilinks-and-frontmatter graph into a navigable canvas. Ctrl/Cmd + G opens the graph view; theme folders cluster naturally; you can edit any node in place and the agent picks up the change. See the View and edit in Obsidian section below.
npx claudepluginhub agentsorg/design-engineering --plugin design-engineeringComprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.