skill▌

$22

Manage multiple local CLI agents in parallel tmux sessions with task assignment and monitoring. \n \n Start, stop, and monitor agents running in isolated tmux sessions with log tailing and health checks \n Assign tasks to specific agents and track their output in real time \n Schedule recurring agent work via cron integration for automated workflows \n Requires tmux and Python 3; agents configured in a local agents/ directory \n

$23

Discover and install complementary skills from the inference.sh registry to expand your AI agent's capabilities. \n \n Browse 150+ available skills across media generation, image processing, audio, search, and social automation categories \n Search, list, and install skills using simple CLI commands ( npx skills search , npx skills add ) \n Pre-configured skill combinations for common workflows: research agents, content creators, and media processors \n Manage installed skills with built-in comm

Expert SwiftUI code review, refactoring, and implementation guidance with iOS 26+ and macOS support. \n \n Covers state management, view composition, performance optimization, and modern SwiftUI patterns across iOS 15+ through iOS 26+ \n Flags deprecated APIs and suggests modern replacements; gates version-specific features with #available and fallbacks \n Addresses lists, layouts, animations, accessibility, Swift Charts, and platform-specific patterns (macOS scenes, Liquid Glass) \n Enforces co

Scaffold and implement authentication in TypeScript/JavaScript apps with Better Auth framework detection, database adapter setup, and OAuth integration. \n \n Detects frameworks (Next.js, SvelteKit, Nuxt, Astro, Express, Hono), databases (Prisma, Drizzle, MongoDB, raw drivers), and existing auth libraries through project scanning \n Supports email/password, OAuth (Google, GitHub, Apple, Microsoft, Discord, Twitter), magic links, passkeys, and phone authentication with configurable email verifica

template-skill

Manage Linear issues, projects, and teams

Category: test

Execute complex tasks across multiple Claude Code sessions with automatic continuation, progress tracking, and two completion mechanisms (promise tags + checkbox counting).