Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
A growing repository of AI agent skills that solves the problem of coding agents having imperfect understanding of the Urbit runtime, Urbit terminal commands, and Urbit-native programming languages like Hoon and Nock.
discover-zig is a skill that provides automatic access to comprehensive Zig skills, including zig-build-system, zig-c-interop, and zig-memory-management.
ClawArmy is an elite "Mission Control" platform for designing, deploying, and synchronizing AI Agent Specialists (Antigravity Skills). It enables developers to synthesize custom agent squads and inject them directly into their local workspaces with zero-friction automation.
🚀 170+ pre-built skills for Claude Code, Cursor, Codex & 14+ AI tools. Stop re-teaching your AI the same things. One command → instant domain expertise. Marketing, SEO, Trading, Video, PM workflows included.
🎭 cc-best: Turn Claude Code into a full dev team — PM→Lead→Dev→QA autonomous workflow. 40 commands · 17 skills · 8 agents · 33 rules · 21 hooks · auto-learning pipeline. | 一个插件，完整开发团队。
Goodable is a local-first Desktop AI Workspace (Desktop Agent Runtime) powered by Claude Agent SDK, combining OS/file control, browser automation, and coding into composable Skills (tool + app modes) to build, run, and publish real AI apps.
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
An AI-powered consultancy system that replicates the breadth and depth of Big 4 firms (Deloitte, PwC, EY, KPMG) using Claude Code's agents and skills framework. A Managing Director orchestrator routes engagements to 9 practice-area partners, each equipped with domain-specific skills delivering board-room-quality deliverables.
Agent skills for building and evaluating apps against official design guidelines. 300+ actionable rules for iOS, iPadOS, macOS, watchOS, visionOS, tvOS, Android, and Web — distilled from Apple HIG, Material Design 3, and WCAG 2.2. Works with Claude Code, Codex, and any agent that supports the Agent Skills format.
Agentic QE Fleet is an open-source AI-powered quality engineering platform designed for use with Claude Code, featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.
intern is a Claude Code skill that automates task delegation using Opencode through ACP.