UI design theory and implementation toolkit combining visual design principles (Gestalt, Fitts's Law, WCAG 2.2, screen archetypes) with source-code-backed component engineering (Radix, CVA, Motion, shadcn v4, Tailwind). Includes design rationale workflow and Claude.ai chat companion skill.
Audit a component, page, or flow for WCAG 2.2 accessibility conformance. Triggers a11y-auditor agent.
Add animation to a component or flow with performance and accessibility awareness. Triggers animation-engineer agent.
Generate a structured design rationale for a screen or component, grounded in design-theory references and concrete tradeoffs. Use when you need to document WHY a design works, justify decisions for PR review, or analyze an existing screen before making changes.
Review a UI component or page for design principle violations, accessibility issues, and polymorphic rendering opportunities. Triggers design-critic and a11y-auditor agents.
Plan or extend a design token system with spacing, color, type, and component variant matrices. Triggers visual-architect agent with design-systems reference.
Audits UI components and pages for WCAG 2.2 accessibility compliance. Use after any interactive component is built. Checks keyboard navigation, focus management, ARIA roles and labels, color contrast, screen reader compatibility, and touch target sizes. Produces a prioritized list of violations with WCAG success criteria references. Invoke when asked to audit, check, or verify accessibility. Examples: - <example>User asks "is this form accessible?"</example> - <example>component-builder finishes an interactive dialog or drawer</example> - <example>User says "run an a11y audit on this component"</example> - <example>User asks "does this meet WCAG 2.2?"</example>
Adds purposeful motion to UI components using Motion spring physics, CSS transitions, and layout animations. Use when motion is explicitly needed — not by default. Invoke when asked to animate a component, add transitions, implement drag gestures, or make motion feel more natural. Always respects prefers-reduced-motion. Examples: - <example>User says "animate this card list so items slide in as they load"</example> - <example>User asks "add a spring animation to this drawer opening"</example> - <example>User wants drag-to-reorder with smooth positional feedback</example> - <example>User asks "why does this animation feel jarring?"</example>
Builds UI components using the correct libraries for the project's existing stack, from headless primitives up. Use when implementing a UI component, page, or feature after the layout has been planned by visual-architect. Greps real library source in refs/ to verify APIs before writing code. Always covers all interaction states. Invoke when asked to build, implement, create, or code a UI component or page. Examples: - <example>User says "build the essay card component from the spec"</example> - <example>visual-architect has produced a layout spec and now implementation starts</example> - <example>User asks "implement the command palette for this app"</example> - <example>User says "add a drawer for mobile filters"</example>
Reviews existing UI for design principle violations, visual hierarchy problems, and polymorphic rendering opportunities. Use when you need to evaluate a component or page against Gestalt principles, Fitts's Law, progressive disclosure, and the design smell catalog. Proactively invoke after component-builder completes any UI work. Also invoke when asked to review, audit, or critique existing UI code. Examples: - <example>User says "review this dashboard component for design issues"</example> - <example>User shares a React component and asks "is this good design?"</example> - <example>component-builder finishes building a feature list component</example> - <example>User asks "why does this UI feel off?"</example>
Maps a project's existing UI technology stack before any work begins. Reads package.json, config files, and source directories to identify framework, CSS approach, component libraries, animation, icons, and any existing design system. Prevents building parallel systems. Always invoke at the start of any UI work on an unfamiliar project. Invoke when asked to detect, identify, or map a project's UI stack. Examples: - <example>Starting work on a new codebase and need to understand what UI libraries it uses</example> - <example>User says "what UI libraries does this project use?"</example> - <example>User asks "before we start, what's in this repo?"</example> - <example>A new project directory is opened and UI work is about to begin</example>
Design principles, visual judgment, and layout architecture for web interfaces. Use when Claude Code needs to evaluate WHY a design works or fails, plan visual hierarchy and layout composition before writing code, choose between design approaches based on user behavior and cognitive load, review existing UI for design principle violations, build or extend a design token system, or reason about accessibility as a design concern rather than a compliance checkbox. Covers color theory, typography and measure, spacing systems, modular ratios, Gestalt principles, Fitts's Law, Hick's Law, progressive disclosure, affordances, signifiers, behavioral design, attention economics, and polymorphic object rendering. Also covers screen archetypes (monitoring, triage, authoring, configuration, exploration) that set density and interaction expectations. Always consult this skill before building new layouts or reviewing existing ones.
Source-code-backed UI implementation expertise for React, Next.js, and Tailwind CSS ecosystems. Use when Claude Code needs to build, refactor, or extend UI components using shadcn, Radix, Vaul, Sonner, cmdk, DaisyUI, Motion, or Tailwind CSS. Use when selecting which library to reach for, building components from headless primitives, adding animation with performance awareness, detecting an existing project's UI stack, or ensuring full state coverage across all interaction states. Greps real library source code rather than relying on training data. Always pair with design-theory for design judgment before implementation.
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.
Most Claude Code plugins give you a set of slash commands and some domain knowledge. These plugins do something different: they learn.
Each plugin in this repo is a domain-specialized engineering intelligence that accumulates knowledge across sessions, grounds itself in real library source code (not training data), and coordinates with a companion chat skill on Claude.ai. The plugin implements. The chat skill plans. Over time, the plugin gets better at its job because it tracks what works, what doesn't, and what it's still uncertain about.
This is the two-surface architecture: one surface for thinking, one for building.
A typical plugin contains four layers:
Specialist agents and slash commands. Each plugin ships with 3 to 7 agents that handle specific subtasks. UI-Design-Pro has a design critic, a component builder, an accessibility auditor, an animation engineer, and a visual architect. Django-Engine-Pro has agents for model design, ORM optimization, migration planning, and MCP server exposure. Agents compose in defined sequences: you always run the stack detector before the component builder, always run the design critic after.
Source-code references. Plugins include install.sh scripts that shallow-clone real library repos into a local refs/ directory. When UI-Design-Pro needs to know how Radix handles focus restoration, it greps the actual Radix source, not its training data. When D3-Pro needs to verify a scale constructor's API, it reads the Observable source directly. This matters because training data goes stale. Source code doesn't.
Skills and decision frameworks. Static knowledge: inheritance decision tables, ORM anti-pattern catalogs, polymorphic rendering rules, animation physics constants. These encode the expert judgment that doesn't change between sessions.
An epistemic knowledge layer. This is the part that learns. Each plugin maintains a knowledge/ directory containing typed claims in JSONL, confidence scores, session logs, and (for some plugins) SBERT embeddings. Claims start as drafts. After review, they become active. Active claims carry Bayesian confidence that updates based on session outcomes: when a suggestion informed by a claim gets accepted, confidence rises; when it gets rejected, confidence drops. Over time, each plugin develops its own body of verified, weighted knowledge about its domain.
Each plugin here has a counterpart: a chat skill that runs on Claude.ai (or Claude Desktop). The division of labor is deliberate.
The chat skill handles planning, reasoning, and decision-making. When you're deciding between DRF and Ninja for an API, or choosing an inheritance strategy for a model hierarchy, or evaluating whether a component needs polymorphic rendering, the chat skill walks you through the tradeoffs and produces a structured handoff document.
The Claude Code plugin handles implementation and learning. It takes the handoff document, builds the thing, greps real source code when it needs to verify an API, logs what it tried, and updates its knowledge base with what it learned.
The chat skill never sees knowledge/claims.jsonl. The plugin never produces planning documents. Each surface does what it's good at.
| Chat Skill (Claude.ai) | Claude Code Plugin |
|---|---|
| Decision frameworks | Slash commands and agents |
| Tradeoff analysis | Source-code grepping |
| Structured handoff docs | Implementation and testing |
| Domain reasoning | Session logging and learning |
| Static (expert knowledge) | Dynamic (knowledge that evolves) |
Every plugin with a knowledge/ directory runs the same protocol:
Session start: Read manifest.json for current state. Load active claims sorted by confidence. Check tensions.jsonl for unresolved conflicts in the task's domain. Surface tensions before making decisions, not after.
During work: Track which claims informed each suggestion. Note when the user accepts, modifies, or rejects a recommendation.
Session end: Write observations to session_log/. Flag contradictions as tension signals. Note recurring patterns the knowledge base doesn't yet cover.
The knowledge types are borrowed from Theseus (a separate epistemic engine project):
Current knowledge stats across the fleet:
| Plugin | Total Claims | Active | Avg Confidence |
|---|---|---|---|
| UI-Design-Pro | 140 | 135 | 0.667 |
| Django-Engine-Pro | 111 | 29 | 0.75 |
npx claudepluginhub travis-gilbert/claude-marketplace --plugin ui-design-proMobile app development specialist: PWA retrofitting, React Native architecture, offline-first sync, mobile API design, touch optimization, and mobile visualization adaptation.
Makes Claude Code extraordinarily good at transforming websites into applications: converting page-based Next.js sites into app-like experiences with persistent layouts, command palettes, and background sync; wrapping them in Tauri desktop shells with native OS integration; and producing architecture handoffs for native Swift/AppKit macOS apps.
Makes Claude Code genuinely good at designing knowledge-graph answer experiences with cosmos.gl on top of DuckDB-WASM, Mosaic, and vgplot. Owns the SceneDirective adapter, the three-picker ControlDock (Position, Weight, Edges), and the recipe library that turns novel ideas into usable images.
Git and deployment automation with verification at every step. Staged file review, conventional commits, pre-commit checks, push with CI/CD detection, and post-deploy health verification.
Makes Claude Code extraordinarily good at building D3 visualizations that are mathematically accurate, physically believable, and aesthetically grounded in the Mike Bostock / Observable canon.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Comprehensive 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
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.
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.