supabase
Gives your app a hosted Postgres database with built-in auth, auto-generated APIs and file storage, and the explorer skill helps you build Studio surfaces like SQL snippets, notebooks and query cells.
Flowy lists 115 plugins for Swift work in Claude Code. Each one bundles skills a Claude Code agent can load while you work. Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
Gives your app a hosted Postgres database with built-in auth, auto-generated APIs and file storage, and the explorer skill helps you build Studio surfaces like SQL snippets, notebooks and query cells.
Skills that help designers and engineers make better UI animation decisions faster, covering when to animate, which properties and curves to use, keeping web motion within the frame budget, and React Native and Expo animation.
Skills for contributors and app developers in the Expo monorepo: write TSDoc for Expo SDK APIs, run Expo's AI code reviewer on changes or pull requests, add Apple App Intents and Siri Shortcuts to Expo apps, and test Expo Router on Android emulators.
Helps designers and engineers make the right animation and interface choices faster, from deciding whether to animate and which properties and curves to use, to keeping motion smooth and finding the exact term for an effect you can only describe loosely.
Lets you create, run and manage Linux containers on your Mac as lightweight virtual machines, so you can build and run Docker-style images without a separate Docker setup. It pulls and pushes standard OCI images from any registry and is optimized for Apple silicon.
Skills and MCP servers for driving computers with AI agents: create and clean up disposable Linux or macOS sandboxes, work inside shared Spaces and a common volume, and automate GUI tasks such as testing forms, taking screenshots, and running end-to-end QA.
Skills for working on the cmux macOS terminal, which is built on Ghostty and shows vertical tabs and notifications for AI coding agents. They cover architecture, backend and billing work, browser automation, and capturing screenshots or recordings of the app.
Lets you control Claude Code sessions remotely from a mobile app, with end-to-end encryption, push notifications and sync across devices. Open source under the MIT license.
Turns PDFs, scanned images, spreadsheets and other documents into clean text, tables and metadata, and splits them into chunks for LLM context windows or search. You can also batch-extract whole folders, pull keywords, and run OCR on scans without a text layer.
Skills and commands for extracting clean text, tables, metadata and keywords from PDFs, scanned images and spreadsheets. Covers OCR, batch processing many files at once, and chunking text for LLM context windows or RAG.
Gives a developer one shared set of agent rules and reusable workflow skills, covering tasks such as controlling your signed-in Chrome, redacting and previewing agent transcripts, and checking ClickClack deploys. Use it to keep several local coding agents working the same way.
An MCP server and CLI that gives AI agents tools to build, test, run, debug, and automate UI on iOS, macOS, watchOS, tvOS, and visionOS projects. Includes skills for both the MCP server and the CLI.
A SwiftUI review skill that checks code for modern API use, deprecated APIs, maintainability, performance, and accessibility such as VoiceOver. Useful when reading, writing, or reviewing SwiftUI projects.
Skills for analyzing and comparing Xcode builds, test runs, app bundles and cache runs with Tuist, including selective testing and cache invalidation diagnosis. Useful for iOS developers tracking build regressions.
Local, clinical AI skills for healthcare data, covering de-identification of protected health information, clinical entity extraction, FHIR bundle assembly, variant annotation, and audit trails for compliance review.
Generates production-ready Lottie animations from a text prompt, so you can create logo, icon, loader and UI motion without hand-writing the JSON. Previews them in a local Skia player while you work with Claude Code, Codex or another coding agent.
Skills for building, deploying, and maintaining Expo and React Native apps with Expo Application Services. Covers EAS builds and store submissions, EAS Hosting, native module migration, and EAS Observe setup.
A SwiftUI component library for iOS developers. Its skills help you browse ready-made components, add a specific view or animation, and build a complete iOS feature from them.
Agent skills for Flutter and Dart development, covering unit tests and mocks with package:test and mockito, coverage reports, CLI app architecture, and fixing runtime errors using stack traces and hot reload.
Agent skills for Dart and Flutter development, covering unit tests, mocks, test coverage reports, command-line app patterns, and fixing runtime errors with hot reload.
Lets an AI agent or MCP client control a computer's desktop apps on macOS, Linux, and Windows through the accessibility layer, without taking over the screen. Use it to automate clicks and typing in apps that have no API.
Skills for working with mlx-serve, a local inference server for Apple Silicon that runs MLX and GGUF models behind OpenAI- and Anthropic-compatible APIs. They help wire apps and scripts to the server for chat, embeddings, image and speech generation, plus benchmarking and releases.
A Chinese-language performance optimization system for Claude Code, bundling skills, agents, commands, hooks and rules for API design, backend patterns, article writing and autonomous loops. Developed through daily use while building real products.
Helps you build Claude Code extensions yourself: write SKILL.md skills, set up hooks that react to events, create MCP servers that give Claude new tools and data sources, plan projects for Claude to execute, and audit agents. Useful once you want to tailor Claude Code to your own workflow.
A plugin for automating routine work with AI models, with approval gates, scheduled routines, and a builder for small local microapps to manage the results. Open source and local-first.
The AI-first 3D & AR SDK for Jetpack Compose, SwiftUI and the web. Declarative 3D and AR for app developers who want a model on screen, or in the room, without a game engine: Filament + ARCore on Android, RealityKit + ARKit on Apple, Filament.js + WebXR in.
A Claude Code skill for building, testing, and driving iOS apps in the Simulator. It runs Xcode builds, launches apps, and taps, types, and swipes through the UI using accessibility labels, with token-efficient scripts.
Agent skills for building iOS apps with Swift and Apple frameworks, covering areas such as Live Activities, AlarmKit, App Clips, accessory setup and ad attribution. Includes MCP servers for Claude Code users.
Open-source Agent Skills for benchmarking and optimizing Xcode build performance across clean builds, incremental builds, compile hotspots, project settings, and Swift Package Manager overhead.
Skills, agents, and commands for Apple platform development in Swift and SwiftUI, covering accessibility, Apple Intelligence, crash log analysis, and performance auditing.
A universal skill installer and package manager for AI coding agents, with skills for backend design, library health checks, prompt improvement, and catalog browsing before install.
Gives AI coding agents guidance for Kotlin work, covering Spring Data JPA entity mapping, migrating Kotlin Multiplatform projects to newer Android Gradle Plugin and Swift Package Manager setups, and porting Gradle builds to the Kotlin Toolchain.
Compliance advisor skills for Claude Code covering CCPA, CIS Controls, CMMC, CSRD and UK Cyber Essentials, with guidance on scoping, gap assessments and consumer rights fulfillment.
Gives Claude Code a team of domain specialists for languages, frameworks, backends, frontends and databases, which it calls automatically or on request. Each brings focused knowledge to the task at hand.
A plugin of skills for maintaining Agent Sessions, a local macOS app for browsing and analyzing AI coding-agent session history. Its skills cover shipping releases, writing release notes, adding support for new agents, and checking session format compatibility.
Helps Apple platform developers move an iOS, macOS or visionOS app from planning to the App Store, with listing copy, ad measurement, search ad campaigns and in-app purchase setup handled for them.
A local-first memory store that combines vector and full-text search, sharing memory with Claude Code over MCP. Includes skills for installing and diagnosing the waxmcp host, Swift client guidance, and performance auditing.
Lets an agent see and steer the other coding-agent and terminal sessions running on your machine or project, listing their status, starting new ones, and sending them prompts or answers. Replaces manual switching between terminal windows.
Helps Claude Code write, convert, and review YAMLScript (.ys) files, including converting Clojure into idiomatic YAMLScript following established style rules.
A Claude Code plugin for planning and producing AI-generated music albums, with skills for album concepts, tracklists, progress dashboards, idea tracking, and album artwork prompts.
A curated collection of 22 plugins for Claude Code, providing specialized agents, skills, and automation tools for development and productivity workflows.
Reviews Swift code for concurrency mistakes, such as misused async/await, actors, Sendable and task groups, and points out modern API choices. Useful when you read, write or review concurrency code and want fewer bugs before they reach runtime.
Skills for building iOS apps that use Meta AI glasses through the Wearables Device Access Toolkit. They cover camera streaming, photo capture, audio streaming, Swift conventions, and live SDK documentation search.
Gives your coding agent step-by-step guidance for common Dart tasks, such as writing unit tests and mocks, collecting coverage reports, building command-line apps, and fixing runtime errors from live stack traces.
A command-line tool that parses xcodebuild and Swift Package Manager build and test output into compact, structured results with errors, warnings and test failures, so coding agents use fewer tokens.
A skill that helps Claude Code write, review, and improve Swift Testing code using current APIs. Useful for projects that test with Swift Testing.
Lets you dictate into any macOS app with a hotkey. Speak, and the corrected text is pasted where your cursor is, with a personal dictionary to fix recurring words.
A skill that reviews Apple platform app code for App Store rejection risks before submission, checking it against Apple's App Store Review Guidelines for iOS, macOS, tvOS, watchOS, and visionOS.
Runs shell commands and AI agents inside a limited user account on your Mac, and can clone the current repo into a sandboxed Claude session for a task.
A Claude Code skill providing the latest OWASP security best practices (2025-2026) for developers building secure applications.
Gives Claude Code and Codex a repeatable development process for planning, reviewing, and shipping changes, so you stop rebuilding the same prompts each time. It also captures corrections and project conventions so future sessions build on what you have already learned.
A security plugin with skills that help AI coding agents write secure code, guide migration of C and C++ code to memory-safe languages, and produce markdown security review reports for a repository.
A native macOS developer tool that uses an AI agent to drive an iOS Simulator, a macOS app, or a web app, so you can run user-style tests on them.
Apple development skills for Claude Code covering SwiftUI, UIKit, Liquid Glass, Human Interface Guidelines, App Store metadata optimization, and framework reference lookups.
A skill that lets an agent running inside Zentty, a native macOS terminal built on Ghostty, discover and split panes, open command overlays, focus panes, launch nested coding agents, and notify the user.
Gives an AI coding agent one house style for Jetpack Compose and Compose Multiplatform code, covering architecture, data, features, platform splits and project setup. The agent then writes screens and modules that follow the same patterns instead of drifting from file to file.
Gives an AI coding assistant expert guidance for low-level work such as custom memory allocators, NUMA-aware memory layout, fast packet I/O with AF_XDP and DPDK, and async I/O with io_uring. Useful when you tune systems code and want fewer trial-and-error cycles.
Organizes scattered AI agent skills into workflows. Lets you inspect, import, enable, disable, deploy, update, repair, and uninstall skill groups through the skill-flow CLI, across coding agents such as Claude Code and Cursor.
Automates capture of marketing screenshots for SwiftUI iOS apps across multiple locales, devices, and appearances, including full-screen shots and isolated element renders. Built as a skill for Claude Code and similar AI coding agents.
A local dashboard that monitors every Claude Code and Codex session on your machine, shows each session's activity as a heartbeat, and lets you approve tool calls from your phone or a strip under the MacBook notch.
A Claude Code plugin with skills, agents and commands for building iOS and macOS features in Swift and SwiftUI. It covers The Composable Architecture, Apple's Foundation Models, GRDB SQLite queries, haptics, and on-demand Swift package API docs.
A Claude Code plugin of custom skills for engineering, Apple app design, product management, content briefs, children's book illustration, and AI architecture, with prompt engineering help for Claude models.
One command for every interface, search, run, and inspect real software across APIs, browsers, desktops, local tools, and MCP.
Turns a local web project or a hosted web app into a macOS Dock-launchable .app with its own native window and Dock icon. Includes Windows beta launchers and static-build packaging for finished sites.
A Claude Code skill for SwiftUI frontend design that produces iOS and macOS interfaces avoiding generic AI-looking patterns. It covers layout, typography, color, spacing and branding.
Turn any website into clean, structured data. Point Crawlberg at a URL and get back Markdown, metadata, and links, from a single page or a whole site, in the language you already use.
A custom Claude Code skill: a strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms.
HomeKit smart home control via MCP, lights, locks, thermostats, and scenes for Claude Desktop, Claude Code, and OpenClaw.
Context-efficient development knowledge via progressive skill discovery.
Skills for a linkyee link-in-bio static site deployed to GitHub Pages: one writes build-time plugins to pull live data such as GitHub stars or blog posts, and one designs custom visual themes.
A Swift project that rebuilds a Claude Code style command line coding agent from scratch, for developers who want to explore how such agents are architected. Includes an example skill.
The best react-native Agent Skills. Forget 10x, this is 100x.
A coding toolkit for Claude Code with machine-enforced safety rules, lifecycle hooks, and reusable skills and agents for testing, accessibility checks, code analysis, and recalling past sessions.
Android & KMP development skills for Claude Code, Codex, and Copilot CLI, architecture, Compose, coroutines, flows, networking, persistence, dependency injection, testing, debugging, and Gradle.
Skills for Claude Code that help developers audit modules, onboard to a codebase, review pull requests, check architecture boundaries, and answer questions about structure, risk, and dependencies.
Lets AI agents debug running programs through the dbg CLI, with breakpoints, stack and variable inspection, and short @ref handles. Covers Node.js, Bun, Python, Java and native code.
Active open-source project ยท MIT tooling with attributed Apple reference content HIG Doctor helps developers and coding agents find interface issues before release.
Claude Code skills for Emacs integration. These skills enable tighter integration with agents running inside Emacs, for example agent-shell.
An agent plugin that teaches your agent to build and manage iOS/macOS projects using native Xcode CLI tools (xcodebuild, xcrun simctl) instead of MCP servers.
Premium SwiftUI animation and interaction skills for AI coding agents, generate production-ready micro-interactions from plain English prompts. Built from legendary-Animo: 84 hand-crafted SwiftUI animation demos.
Build and sign Stellar transactions, query Horizon, and interact with Soroban smart contracts via RPC. Communicate with anchors and external services using the built-in SEP protocol support.
A set of installable skills for AI coding agents covering iOS and macOS development in Swift and SwiftUI, bug review and QA, SwiftUI animation patterns, and wave-based parallel task orchestration.
Skills for AI coding agents working with Apollo GraphQL, covering Apollo Client for React, Apollo Federation subgraph schemas, Apollo iOS and Apollo Kotlin, plus an MCP server and Rover CLI.
Apple-authored SwiftUI and Apple platform guidance, packaged as skills for AI coding agents.
A native macOS menu bar app that proxies Claude Code, Codex, Gemini, Kimi, GitHub Copilot, Junie, and Grok authentication for use with Droids. Built on CLIProxyAPI.
A minimal rule system for Claude Code. Gives Claude the structural discipline it lacks by default, phase tracking, decision logging, honest pushback, debug discipline, language-specific best practices, and reusable skills.
Teaches Claude how to instrument mobile apps correctly, what to measure, what context to attach, and what mistakes to avoid.
Beagle is an agent skills collection for Claude Code users, offering framework-aware code review, documentation, testing, architecture guidance, and git workflows. It includes skills for LangGraph and Deep Agents projects.
Gives Claude Code tools for the Amiga: searching the Aminet package archive, downloading and verifying packages, installing them, and setting up the FS-UAE emulator to run them. Replaces a manual hunt through archive listings and emulator configuration.
Build, test, and archive Swift packages and Xcode projects for Apple platforms with Claude Code.
A token-efficient security triage skill for Claude Code that runs a staged LLM static analysis pipeline inside a single session using the agent's own Read, Grep and Glob tools. It needs no external scanner.
Describe your goal, approve the spec, then step away, Claude and Codex loop together until it's right.
Claude Code skills for founders, developers, and web3 builders. This repository publishes reusable skill folders under skills//, ships stable bundle downloads through GitHub Releases, and publishes changed skills to ClawHub.
Gives AI agents domain expertise for regulated business work, covering finance, banking, legal and sales tasks such as reconciliation, KYC risk rating and AML checks. It encodes business rules and regulatory knowledge so an agent can carry out these workflows on its own.
A Claude Code skill that gives a prioritized design critique of a UI from a URL, screenshot, or component file. It covers visual hierarchy, typography, spacing, color and contrast, motion, component states, and responsiveness.
Gives Claude Code a supervised team of expert agents that write code, plus hooks that check quality as it is written and skills that bring in framework knowledge, so Claude follows your architecture instead of guessing.
Gives your Claude Code session a structured pipeline for building software, from specs and plans through code, review and pull requests. Each stage leaves a plain Markdown artifact that feeds the next, so nothing is orphaned.
A library of skills for Claude Code that guides building and auditing code to current engineering standards, covering APIs, architecture, async and concurrency, C and C++, and CLI design.
A skill for writing Swift code for Apple platforms such as iOS, macOS and visionOS. It covers Swift concurrency, SwiftUI, MVVM architecture, Metal GPU programming and RealityKit.
A completion gate for Claude Code that refuses to accept done without evidence. It checks tests, TODOs, and the original requirements before a task may end, with skills for asking for proof and catching forgotten promises.
Open-source Agent Skills for automated visual testing and accessibility setup of iOS/SwiftUI applications using Claude Code's computer use.
Agent skills that help developers build applications with PowerSync.
A Claude Code plugin with agent skills that teach the AI assistant to set up and use rudder-cli, import and evolve RudderStack resources as YAML, manage transformations, and generate type-safe Swift and Kotlin tracking SDKs from tracking plans.
Coordinates a team of specialist AI agents for software work, handing tasks to architecture, backend, database, frontend, iOS and DevOps roles so larger builds run without you routing each step by hand. Ships with reusable patterns for API design review, database schemas and orchestration.
A macOS menu bar app that pops a floating notification in the center of your screen when Claude Code needs you.
Post-production for screen recordings without a GUI: it speeds up idle stretches, zooms automatically on click clusters, adds keystroke overlays, smooths the cursor, and exports vertical video for social posts.
Stuff for Agents on macOS Promo audio: Socket Codex Marketplace Promo.
Gives Claude Code the author's own working judgment for writing code in specific languages and platforms, so its output follows experienced practice instead of generic defaults.
Helps AI agents such as Claude Code remove personal data from data broker sites and request account deletion and opt-outs. Intended for users who want to reduce their online personal data footprint.
A Claude Code plugin of skills for Swift and Apple-platform app development. It covers App Store review preparation, Apple design guidelines, privacy and legal compliance, and code signing and release steps.
Skills and commands for iOS and backend work, covering Xcode build benchmarking, Swift Package Manager dependency analysis, Jira task creation from meeting notes, and searching local knowledge docs.
A team of AI agents for building iOS and Android apps from a plain idea, covering planning, design, development, code review, QA, and release. Suits developers who want a structured studio workflow inside Claude Code.
A Claude Code plugin that reviews your project with a committee of AI personas chosen for its phase. A profiler reads the project and interviews you, then picks which reviewers take part.