Search skill packs and skills together

Container-based Azure agents require precise SDK, identity, image, and protocol configuration. This skill provides focused Python patterns for creating and managing hosted agents.

Projects often need custom visuals for interfaces, documentation, and design work. This skill provides a Google Gemini workflow for creating and saving PNG assets.

Stateful agent systems can become hard to trace and maintain. This skill helps Claude, Codex, and Claude Code design clearer LangGraph workflows.

Production LangChain agents need clear architecture, memory, evaluation, and observability. This skill guides Claude, Codex, and Claude Code through LangGraph patterns, async tools, RAG, testing, and deployment.

Developers need reliable patterns for Microsoft 365 agents across Teams and Copilot Studio. This skill provides TypeScript examples for routing, hosting, streaming, and Copilot Studio integration.

Agents lose continuity when memory architecture does not match persistence, retrieval, and reasoning needs. This skill guides selection and design across layered memory approaches.

Single-agent designs can hide assumptions, constraints, and failure modes. This skill runs a gated review with specialized agents and records every decision.

Windows PowerShell scripts often fail because of syntax, path, encoding, and null handling issues. This skill gives concise patterns for safer, more predictable scripts.

React teams need consistent patterns for components, hooks, state, performance, and testing. This skill gives Claude, Codex, and Claude Code concise guidance for production React decisions.

AI-built interfaces can drift into inconsistent patterns and unclear design choices. This skill gives agents focused constraints for interface work.

React and Next.js apps often lose speed through waterfalls, large bundles, and avoidable re-renders. This skill gives agents focused rules for reviewing and improving performance-sensitive code.

Agents can claim success before checking real evidence. This skill requires fresh verification commands and evidence before completion claims.