CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
dadederk avatar

Ios Accessibility

dadederk/ios-accessibility-agent-skill
593 installs162 stars
Summary

This one's for when you're building iOS apps that need to work with VoiceOver, Dynamic Type, Switch Control, and other assistive technologies. It covers both UIKit and SwiftUI implementations with a pragmatic approach: accessibility from the start, not as an afterthought. The guidance is opinionated in good ways, like avoiding "Close button" labels (VoiceOver already says "button") and preferring native components over custom builds. It includes decision trees for common scenarios, anti-patterns to dodge, and manual testing workflows alongside code fixes. The agent won't just throw fixes at you without considering actual user impact across different assistive technologies.

Install to Claude Code

npx -y skills add dadederk/ios-accessibility-agent-skill --skill ios-accessibility --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub

iOS Accessibility

Overview

This skill provides expert guidance on iOS accessibility, covering VoiceOver, Dynamic Type, assistive technologies, inclusive design practices, and both UIKit and SwiftUI implementations. Use this skill to help developers build apps that work for everyone.

The Approach

  • Shift-left — Accessibility is part of the process. It needs to be considered even in prototypes or MVPs.
  • User-centric — Accessibility is about people. Checklists help, but the goal is not checklist compliance. The goal is to offer a great experience for users with disabilities.
  • Progress over perfection — Anytime is a good time to start. Focus on iterative and incremental improvements as you go. It goes a long way.
  • Test as you go — Manual testing is part of development.

Agent Behavior Contract

  1. Accessibility is non-deterministic. Propose potential solutions in order of confidence and present with clear pros, cons, and trade-offs.
  2. Before proposing fixes, identify the platform (UIKit vs SwiftUI) and the assistive technology, accessibility feature, or design consideration in context.
  3. Do not recommend accessibility fixes without considering the user experience impact.
  4. Prefer manual testing guidance alongside code changes, together with any automated or semi-automated solutions.
  5. Cross-reference multiple assistive technologies when relevant (VoiceOver, Voice Control, Switch Control, Full Keyboard Access).

Anti-Patterns to Avoid

  • Do not add trait names to labels — Say "Close", not "Close button" (VoiceOver adds "button" automatically, when using the button trait)
  • Do not use .accessibilityHidden(true) on interactive elements — Users won't be able to access them
  • Do not use fixed font sizes — Always use text styles for Dynamic Type support
  • Do not use hardcoded colors for text — Use semantic colors (.label, .secondaryLabel) for contrast and Dark Mode
  • Do not group UIKit elements without a clear combined label — If isAccessibilityElement = true, set accessibilityLabel (and value/traits as needed).
  • Do not group SwiftUI elements without a clear combined label — If .accessibilityElement(children: .ignore) is used, provide label/value/traits manually.
  • Do not add hints unless needed — It should be clear what a component expresses, and does, by its label/value/traits. Only configure for adding extra clarity or context.
  • Do not rely on onTapGesture alone — Prefer semantic controls like Button. If gesture handling is unavoidable, add button traits and clear labels.
  • Do not scale chrome controls with Dynamic Type — For navigation bars, toolbars, and tab bars, prefer Large Content Viewer (iOS 13+) using .accessibilityShowsLargeContentViewer / UILargeContentViewerItem.

General Guidance

Prefer native components: Whenever possible, use Apple's native components and customize them to your needs instead of building custom components from scratch.

Design system first: Whenever the project uses a design system of its own (colors, text styles, component catalog), propose changes in the design system itself so the improvement snowballs everywhere in the app using an improved component.

Platform parity: The same accessibility principles apply to both UIKit and SwiftUI, but APIs and implementation details differ.

Project Settings Intake (Evaluate Before Advising)

Before providing accessibility guidance, determine:

Project Capabilities

  • Is the project using SwiftUI, UIKit, or a mix of both?
  • iOS deployment target — Some APIs require specific versions:
    • iOS 13+: Large Content Viewer (UILargeContentViewerInteraction), SF Symbols
    • iOS 14+: Switch Control action images (UIAccessibilityCustomAction.init(name:image:actionHandler:))
    • iOS 15+: AccessibilityFocusState, .accessibilityRotor
    • iOS 16+: .accessibilityRepresentation, .accessibilityActions { } syntax
    • iOS 17+: .sensoryFeedback
  • Check minimum OS — Look for #available checks and deployment target in project settings

Project Conventions

  • Design system — Does the project define its own design system (colors, text styles, UI component catalogue)? Propose changes in the design system when appropriate, not only per-feature.
  • Semantic colors and text styles — Does the project use semantic colors (.label, .systemBackground) and text styles (.preferredFont(forTextStyle:) in UIKit, .font(.body) in SwiftUI) vs hardcoded values?
  • Existing accessibility patterns — Search for .accessibilityLabel, .accessibilityTraits, etc. to match project style.
  • Localization — Accessibility labels, values, and hints should be localized. Match the project's localization conventions.
  • UI construction — Interface Builder (XIB/Storyboard) or code-only?
  • Custom gestures — Identify if custom gestures need accessible alternatives.
  • Accessibility test coverage — Existing UI tests auditing for accessibility?

When Settings Are Unknown

If you can't determine the above, ask the developer to confirm before giving version-specific or framework-specific guidance.

Quick Decision Tree

When a developer needs accessibility guidance, follow this decision tree:

  1. VoiceOver issues?

    • Core concepts: Read references/voiceover.md
    • UIKit implementation: Read references/voiceover-uikit.md
    • SwiftUI implementation: Read references/voiceover-swiftui.md
  2. Dynamic Type, text scaling, or adaptive layout?

    • Core concepts: Read references/dynamic-type.md
    • UIKit implementation: Read references/dynamic-type-uikit.md
    • SwiftUI implementation: Read references/dynamic-type-swiftui.md
  3. Other assistive technologies?

    • Voice Control: Read references/voice-control.md
    • Switch Control: Read references/switch-control.md
    • Full Keyboard Access: Read references/full-keyboard-access.md
  4. Testing accessibility?

    • Manual testing: Read references/testing-manual.md
    • Automated testing: Read references/testing-automated.md
  5. Cross-cutting concerns?

    • Contrast, targets, motion, haptics: Read references/good-practices.md
    • Culture and mindset: Read references/concepts-and-culture.md
  6. Quick reference needed?

    • Common mistakes, patterns, checklists: Read references/playbook.md
  7. Need definitions or sources?

    • Glossary: Read references/glossary.md
    • Sources and further reading: Read references/resources.md

Quick Playbook (Start Here)

  1. Confirm framework (UIKit vs SwiftUI) and iOS target.
  2. Identify assistive technology and user-experience issue.
  3. Use the Decision Tree and jump into the relevant reference file.
  4. Whenever it makes sense, provide 2-3 options with trade-offs and expected UX impact.
  5. Always include testing guidance alongside any code changes.

For common mistakes, inspector warnings, code patterns, version-specific APIs, and checklists, use references/playbook.md.

Example Prompts and Expected Shape

Example prompt: “VoiceOver reads ‘button’ for my close button.” Expected response:

  • Confirm framework and iOS target if unknown.
  • Provide options when there are multiple viable approaches (for example, add an accessibility label vs a labeled button using icon-only style), with trade-offs.
  • Include a framework-appropriate snippet.
  • Add testing steps (VoiceOver, Voice Control...).

Example prompt: “Dynamic Type breaks my header layout in UIKit.” Expected response:

  • Confirm preferredContentSizeCategory handling and iOS target.
  • Suggest layout adaptation strategies (stack axis change vs constraints).
  • Include a UIKit snippet and testing steps at Large Accessibility Sizes.

Edge Cases and Gotchas

  • Mixed UIKit/SwiftUI screens: use correct API set per view layer.
  • Custom controls or gestures: always provide a VoiceOver/Voice Control alternative.
  • Unknown iOS target: ask before suggesting version-specific APIs.
  • No code context: ask for relevant view code or a screenshot of the Accessibility Inspector.
  • Localization: all labels, values, and hints (and any other string parameter like custom content, or accessibility announcements, etc.) must be localized.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
AI & Agent BuildingMobile DevelopmentDesign & UI/UX
First SeenJun 3, 2026
View on GitHub

Recommended

More AI & Agent Building →
aj-geddes avatar
fastapi-development

aj-geddes/useful-ai-prompts

Build high-performance FastAPI applications with async routes, validation, dependency injection, security, and automatic API documentation. Use when developing modern Python APIs with async support, automatic OpenAPI documentation, and high performance requirements.
590
317
heygen-com avatar
liveavatar-feedback

heygen-com/liveavatar-agent-skills

Collect and submit developer feedback to the LiveAvatar team. Use when: (1) A LiveAvatar integration is done, working, finished, or complete, (2) The user says "it works", "we're done", "that's it", "ship it", (3) The user is frustrated, stuck, or giving up — "this is broken", "this doesn't work", "I'm stuck", "I give up", "this is frustrating", "I want to report an issue", (4) The user explicitly asks to give feedback, report a bug, file an issue, or share a suggestion about LiveAvatar, (5) You've seen 3+ failed attempts at the same integration step, (6) You just finished writing or generating LiveAvatar integration code for the user.
590
5
hyva-themes avatar
hyva-cms-component

hyva-themes/hyva-ai-tools

Create custom Hyvä CMS component. This skill should be used when the user wants to create a new Hyvä CMS component, build a Hyvä component, or needs help with components.json and PHTML templates for Hyvä CMS. Trigger phrases include "create hyva cms component", "add cms component", "new hyva component", "build page hyva cms element", "custom cms element".
590
78
orchestra-research avatar
systems-paper-writing

orchestra-research/ai-research-skills

Comprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.
590
11.5k
bbeierle12 avatar
gsap-scrolltrigger

bbeierle12/skill-mcp-claude

Scroll-based animations using GSAP ScrollTrigger plugin including pinning, scrubbing, snap points, and parallax effects. Use when creating scroll-driven animations, sticky sections, progress indicators, or parallax scrolling experiences.
588
8
aj-geddes avatar
static-code-analysis

aj-geddes/useful-ai-prompts

Implement static code analysis with linters, formatters, and security scanners to catch bugs early. Use when enforcing code standards, detecting security vulnerabilities, or automating code review.
585
317