Agent Skills Hub

agent-system

Implementation patterns for MERIDIAN autonomous AI agents using Claude API, including BaseAgent lifecycle, structured tool use, token budget enforcement, and cron scheduling.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.

codex-cli

Orchestrate Codex CLI for efficient parallel coding, task automation, and session-managed workflows to optimize token usage and development speed.

clawteam

Orchestrate multi-agent AI swarms using the ClawTeam CLI to automate parallel task execution, dependency management, and team collaboration with git worktree isolation and tmux support.

gdoc

Reliably read and extract content from publicly shared Google Docs using curl for full document retrieval.

prompt-injection-test

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

youtube_moderation_prototype

A prototype skill for automating YouTube live chat moderation using pattern-based detection for spam, toxic content, and rate limiting, optimized for testing agent reliability before deployment.

cascade-orchestrator

Advanced workflow orchestration for AI agents, featuring multi-model routing, Codex sandbox iteration, parallel swarm execution, and persistent memory across complex pipelines.

pavlok

Trigger Pavlok hardware stimuli (vibe, beep, or zap) via API to enforce habits or provide physical feedback for task management.

milady-development

Self-modify your Milady agent by managing plugins. Edit code, rebuild, and restart the runtime to develop new capabilities or improve agent workflows locally.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

Create New Skills

A framework for creating reusable Claude Code agent skills, following best practices for directory structure, progressive disclosure, and multi-file patterns.