Agent Skills Hub

multi-tenant-isolation

Enables multi-tenant isolation for AI agent swarms, ensuring strict data separation, process isolation, and secure resource management between deployments.

code-security

Comprehensive secure coding guidelines for 15+ languages, covering OWASP Top 10, infrastructure security, and best practices to identify vulnerabilities in code, configurations, and cloud setups.

opper-api

Direct access to the Opper REST API for LLM orchestration, model management, task execution, and seamless migration from OpenAI, Anthropic, or OpenRouter.

code-review

Perform comprehensive code reviews with a focus on security vulnerabilities, performance optimization, maintainability, and code correctness.

building-ai-agent-on-cloudflare

Build stateful AI agents on Cloudflare Workers using the Agents SDK. Features real-time WebSockets, persistent state management, scheduled background tasks, and native tool integration for production-ready deployments.

debug-firewall

Debug the AWF (Agentic Workflow Firewall) by inspecting containers, analyzing Squid logs, checking iptables, and troubleshooting network or domain access issues in isolated sandboxes.

agno

Framework for building multi-agent systems, AgentOS runtimes, and MCP-integrated AI agents.

swagger-petstore-openapi-3-0

A structured API interface for the Swagger Petstore, optimized for AI agents to interact with resources like pets, users, and store orders using on-demand documentation loading.

qc

Automated quality gate using 5 parallel AI agents to review code changes for correctness, style, and consistency.

state-management

Guidance on frontend state management, including global stores like Zustand/Pinia, server state via TanStack Query, and URL state handling.

claude-code-guide

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

vibe-run

A deterministic orchestration engine for autonomous coding agents, managing workflow loops, state persistence, and checkpoint-based execution.