By themizeguy
Principal-engineer-grade Apple UI specialist. 7 Opus agents that design, review, optimize, and craft iOS UI so it feels like Apple built it. Covers Liquid Glass, spring animations, haptic design, accessibility, SwiftUI performance, and deep platform integration (widgets, Live Activities, App Intents). Four skills: design-ios (greenfield screen/flow creation), review-ios-ui (HIG + visual + interaction audit), optimize-ios-ui (animation + haptics + performance tuning), craft-ios-ui (full 6-specialist team sweep). Backed by 23 self-contained reference files covering design, animation, haptics, accessibility, performance, and platform integration. Read-only review by default; the orchestrator applies findings only on explicit user approval.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Use this agent when the user wants a comprehensive iOS accessibility audit. Deep specialist in VoiceOver, Dynamic Type, color contrast, touch targets, Reduce Motion, Reduce Transparency, Switch Control, Voice Control, Large Content Viewer, Smart Invert, and WCAG 2.2 compliance for iOS. Reviews SwiftUI accessibility modifiers, traits, grouping, custom actions, and rotor. Returns severity-tagged findings with concrete SwiftUI fixes. Read-only. Backed by Opus with accessibility reference files, serena, and Context7. Examples: <example> Context: User wants to make sure their app is accessible before submission. user: "audit my app for accessibility" assistant: "I'll dispatch the accessibility-engineer to review VoiceOver, Dynamic Type, contrast, touch targets, and all motor accessibility dimensions." <commentary> Full accessibility audit is this agent's primary purpose. </commentary> </example>
Use this agent when the user wants expert review or optimization of iOS animations and haptic feedback. Deep specialist in SwiftUI spring physics, PhaseAnimator, KeyframeAnimator, matchedGeometryEffect, gesture-driven animation, symbol effects, Core Haptics, SwiftUI .sensoryFeedback, AHAP patterns, and the Apple philosophy that animation communicates and haptics confirm. Reviews for feel, timing, purpose, and Reduce Motion compliance. Returns severity-tagged findings with exact spring parameters and haptic placements. Read-only. Backed by Opus with animation + haptics reference files, serena, and Context7. Examples: <example> Context: User's animations feel sluggish or generic. user: "my animations don't feel right, they feel web-like" assistant: "I'll dispatch the animation-haptics-engineer to audit spring parameters, timing, and animation purpose against Apple's motion philosophy." <commentary> Animation feel is this agent's core expertise. </commentary> </example> <example> Context: User wants to add haptic feedback to their app. user: "where should I add haptics in my app?" assistant: "I'll dispatch the animation-haptics-engineer to map every interaction surface and recommend specific haptic types and triggers." <commentary> Haptic design audit is equally core to this agent. </commentary> </example>
Use this agent when the user wants to design new iOS UI from scratch -- a screen, a flow, a component family, or a full app interface. This is a 40-year Apple principal engineer who designs production-grade SwiftUI that feels like Apple built it. Commits to Apple's design language: Liquid Glass, spring animations, semantic colors, SF Symbols, proper navigation hierarchy, and intentional haptic feedback. Produces code you can drop into Xcode and build. Backed by Opus with 22 self-contained reference files, serena project navigation, and Context7 for live Apple framework docs. Examples: <example> Context: User wants a new settings screen for their iOS app. user: "design the settings screen for my app" assistant: "I'll dispatch the apple-ui-architect agent to design a settings screen with proper NavigationStack hierarchy, grouped forms, and Apple-native patterns." <commentary> Greenfield UI design is this agent's primary use case. Dispatch with project context. </commentary> </example> <example> Context: User wants a detail view with hero animation from a list. user: "build me a list-to-detail flow with a hero transition" assistant: "I'll dispatch the apple-ui-architect to create the flow with matchedGeometryEffect and proper spring timing." <commentary> Creating interaction flows with animation is core to this agent's expertise. </commentary> </example>
Use this agent when the user wants a comprehensive Apple HIG and visual design quality review of existing SwiftUI or UIKit code. Reviews Liquid Glass adoption, typography hierarchy, semantic color usage, SF Symbols, navigation patterns, spacing/layout, and overall Apple-native feel. Returns severity-tagged findings with concrete SwiftUI rewrites. Read-only. Backed by Opus with the 22-file reference library, serena, and Context7. Examples: <example> Context: User finished a new screen and wants to know if it feels Apple-native. user: "does this screen feel like an Apple app?" assistant: "I'll dispatch the apple-ui-reviewer agent to audit against HIG, Liquid Glass, typography, color, spacing, and navigation patterns." <commentary> Visual design quality audit is this agent's primary use case. </commentary> </example>
Use this agent to orchestrate a comprehensive multi-pass Apple UI improvement that dispatches all specialist agents. Used by the craft-ios-ui skill to coordinate a full audit -> plan -> apply cycle. Dispatches apple-ui-reviewer + animation-haptics-engineer + accessibility-engineer + performance-engineer + platform-engineer in parallel, then merges findings, prioritizes, and presents a unified report. Team-mode orchestrator -- only invoke for the full craft-ios-ui workflow, not single-dimension reviews. Examples: <example> Context: User wants the full treatment on their iOS UI. user: "make this app feel like Apple built it" assistant: "I'll dispatch the craft-team-lead agent to coordinate all 6 specialists for a complete UI craft audit." <commentary> Full multi-agent UI improvement is this orchestrator's purpose. </commentary> </example>
Comprehensive multi-agent Apple UI improvement. Dispatches craft-team-lead which orchestrates all 5 review specialists (apple-ui-reviewer, animation-haptics-engineer, accessibility-engineer, performance-engineer, platform-engineer) for a full audit -> plan -> apply cycle. The heavy-hitter skill. Use when the user wants the complete treatment: "make this feel like Apple built it", "full UI pass", "craft this to Apple quality", "make this world-class iOS UI". Takes 10-30 minutes depending on project size. Read-only review by default; applies findings only on explicit user approval.
Design new iOS UI from scratch -- a screen, a flow, a component, or a full app interface. Dispatches the apple-ui-architect Opus 4.7 agent which produces production-grade SwiftUI with Liquid Glass, spring animations, semantic colors, SF Symbols, proper navigation hierarchy, intentional haptic feedback, and full accessibility from birth. Triggers on "design a [screen/flow/component]", "build me a [screen]", "create the UI for", "design the [dashboard/settings/onboarding]".
Optimize iOS UI animations, haptics, and rendering performance. Dispatches animation-haptics-engineer (motion tuning + haptic placement) and performance-engineer (body evaluation, scroll, image handling, rendering) in parallel. Merges findings into a unified optimization report. Triggers on "optimize my animations", "improve haptics", "fix scroll jank", "optimize iOS UI performance", "make animations smoother", "add haptics", "tune springs".
Review existing iOS UI code for Apple-native quality. Dispatches 3 specialists in parallel: apple-ui-reviewer (HIG + visual + Liquid Glass), animation-haptics-engineer (motion + tactile), and accessibility-engineer (VoiceOver + Dynamic Type + contrast + motor). Merges findings into a unified report with per-dimension verdicts. Triggers on "review my iOS UI", "check this screen", "does this feel Apple-native?", "audit the UI", "HIG review", "is this accessible?".
Uses power tools
Uses Bash, Write, or Edit tools
A team of 7 Opus specialists embodying a 40-year principal Apple UI engineer. Designs, reviews, optimizes, and crafts iOS UI so it feels like Apple built it. Liquid Glass done correctly. Springs that settle naturally. Haptics that confirm without fatiguing. Accessibility built in. Platform integration that makes the app feel like it belongs on the home screen.
Bridges the gap between "code that compiles" and "UI that feels right." Existing iOS review tools cover App Store compliance, privacy, security, and engineering correctness. This plugin covers the CRAFT layer:
Run standard code review tools for "will Apple accept this?" Run apple-ui-craft for "will users love this?"
Install this plugin into Claude Code via the plugin marketplace system, or clone directly:
git clone https://github.com/TheMizeGuy/apple-ui-craft-public.git
Then add it as a Claude Code plugin using the plugin configuration mechanism.
| Skill | Triggers | Agents | Scope |
|---|---|---|---|
apple-ui-craft:design-ios | "design a [screen/flow/component]" | 1-2 | Greenfield creation |
apple-ui-craft:review-ios-ui | "review my iOS UI", "check this screen" | 3 | Visual + animation + a11y audit |
apple-ui-craft:optimize-ios-ui | "optimize animations", "fix scroll jank", "add haptics" | 2 | Motion + performance tuning |
apple-ui-craft:craft-ios-ui | "make this feel Apple-native", "full UI pass", "make this god tier" | 6 | Full multi-agent team sweep |
| Agent | Domain |
|---|---|
apple-ui-architect | Greenfield design + production SwiftUI |
apple-ui-reviewer | HIG + visual + Liquid Glass audit |
animation-haptics-engineer | Motion + tactile feedback |
accessibility-engineer | VoiceOver, Dynamic Type, full a11y |
performance-engineer | SwiftUI rendering, scroll, memory |
platform-engineer | Widgets, Live Activities, App Intents, system depth |
craft-team-lead | Multi-agent orchestrator |
23 self-contained reference files covering every dimension of Apple UI craft:
references/
design/ (7 files: philosophy, Liquid Glass, typography, color, SF Symbols, layout, navigation)
animation/ (5 files: fundamentals, spring physics, advanced animators, transitions, gestures)
haptics/ (3 files: design principles, SwiftUI sensory feedback, Core Haptics engine)
accessibility/ (4 files: VoiceOver, Dynamic Type, visual, motor)
performance/ (2 files: SwiftUI rendering, scroll/list)
platform/ (2 files: widgets/Live Activities, App Intents/system)
| Tag | Meaning |
|---|---|
| CRITICAL | Breaks user experience (a11y blocker, < 44pt touch target, missing Reduce Motion) |
| HIGH | Degrades experience noticeably (wrong navigation, missing haptics, animation fights user) |
| MEDIUM | Quality gap (suboptimal spring, generic spacing, missing SF Symbol) |
| LOW | Polish (slightly better timing, additional haptic surface) |
| NIT | Taste preference (sparing) |
"design the settings screen for my app"
-> design-ios skill -> apple-ui-architect
"review my iOS UI"
-> review-ios-ui skill -> 3 specialists in parallel
"my animations feel sluggish"
-> optimize-ios-ui skill -> animation-haptics-engineer + performance-engineer
"make this feel like Apple built it"
-> craft-ios-ui skill -> craft-team-lead orchestrates all 6 specialists
Pull requests welcome. Keep the anti-AI-slop bar high: no emojis, no hedge words, no trailing summaries, no generic transitions. If adding a new reference file, mirror the existing structure (heading hierarchy, tables over prose, concrete code, cross-references).
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 claimnpx claudepluginhub themizeguy/apple-ui-craft-publicClaude Code plugin that dispatches an Opus 4.6 agent to execute any Railway infrastructure task end-to-end. CLI-first, GraphQL when the CLI lacks a mutation, Playwright against the dashboard for UI-only actions. Applies known Railway gotchas automatically, verifies after every mutation, and returns structured reports.
Expert API design, review, debugging, optimization, security auditing, spec generation, migration, and deprecation. Opus 4.7 agent backed by embedded reference files covering architecture patterns, schema design, authentication, authorization, security hardening, client access, performance, observability, testing, inter-service communication, and API lifecycle. Handles REST/GraphQL/gRPC/tRPC/Connect, OAuth 2.1/OIDC, multi-tenancy, RFC 9457 errors, rate limiting, OTel observability, and the full API lifecycle from spec to sunset.
Expert CI/CD pipeline architect, reviewer, optimizer, debugger, and security auditor. Opus agent backed by a comprehensive embedded knowledge base covering GitHub Actions, GitLab CI/CD, Jenkins, Buildkite, Tekton, and Kubernetes-native stacks. Self-hosted runner fleet design, supply chain security (SLSA/Sigstore/SBOMs), progressive delivery, DORA metrics, and cross-platform migration.
TypeScript 6 UI engineering team. Designs, reviews, optimizes, and improves UI code so it looks like a human design team built it — distinctive aesthetic point-of-view, OKLCH color systems, variable typography, motion with spring physics, sub-2.5s LCP, sub-200ms INP, sub-0.1 CLS, and TS6 strict-mode type safety with branded primitives, discriminated unions, and exhaustiveness. Six Opus specialists (design architect, design reviewer, performance engineer, TypeScript engineer, anti-AI auditor, team lead) backed by self-contained references on TS6, Tailwind v4 + OKLCH + APCA, anti-AI-aesthetic patterns, Core Web Vitals, WCAG 2.2 + reduced motion, and component architecture (compound, polymorphic, slot). Four user-invoked skills: typescript-design-ui, typescript-review-ui, typescript-optimize-ui, typescript-improve-ui. Read-only by default; the orchestrator applies findings only on explicit user approval.
Opus 4.6 kanban board manager and story architect. Creates stories from plans, manages per-story markdown files as source of truth, generates Obsidian Kanban board views, maps dependencies as Mermaid DAGs, audits backlogs, reconciles board state with git, plans parallelizable dispatch waves, computes flow metrics, and generates session-scoped stop hooks. Dispatches Sonnet scout runners for read-only reconnaissance.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
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.
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.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
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.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.