Agent Skills Hub

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

Damage Control

Defense-in-depth protection for Claude Code. Manage security hooks to block dangerous commands, enforce file access controls, and protect sensitive paths across global or project-specific scopes.

claude-code-guide

An advanced development guide for Claude Code, covering REPL environments, MCP integration, development workflows, and best practices for AI-assisted coding.

social-push

Automate social media content publishing using agent-browser to draft posts on platforms like Xiaohongshu, X, Weibo, WeChat, and Juejin directly from your browser.

ai-multimodal

Process and generate multimedia with Google Gemini. Analyze audio, images, videos, and PDFs with high-context windows. Supports transcription, visual QA, OCR, and AI-driven image creation.

Swarm Orchestration

Orchestrate multi-agent swarms using agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Ideal for building distributed AI systems and scaling complex development workflows.

hs

Pre-execution security guardrails for AI agents. Validates shell commands and file reads against 400+ security patterns to block destructive operations, credential theft, and unauthorized system access.

go

Autonomous recursive execution engine for indiiOS that manages task completion, state verification, and error handling.

mls

Unified local ML inference server for ASR, TTS, Translation, Image Generation, and Vision on Apple Silicon, powered by MLX.

prompt-injection-test

A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.

cowork-router

Dynamic meta-router for managing and orchestrating multi-domain AI coding agent skills across plugins and projects.

creating-opencode-agents

Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.