Agent Skills Hub

pattern-detection

Analyze and identify codebase patterns (naming, architecture, testing) to maintain consistency and enforce standards during development.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

git-ship

Automate your entire Git lifecycle from commit and PR creation to CI monitoring and branch merging, enforcing conventional commits throughout.

wrap

Automated session cleanup and documentation tool. Proactively updates CLAUDE.md, detects automation patterns, extracts insights, and organizes pending tasks.

sui

Debugs deterministic Sui simtest failures using automated logging and the scientific method.

plugin-development

Develop, test, sign, and publish governance plugins for Memoria using Rhai or gRPC runtimes. Manage the full plugin lifecycle from scaffolding to activation.

FastMCP Development

Build and manage MCP servers using the FastMCP framework. Guide for creating tools, resources, prompts, Claude Desktop integration, and deployment with Python and TypeScript.

context-engineering-collection

A structured repository of Agent Skills for context engineering, multi-agent architectures, and production-grade agent system optimization.

agno

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

video-subtitle-cutter

Automate video editing by using Whisper to transcribe and AI to identify filler words, pauses, and mistakes, then generating optimized FFmpeg commands for clean, professional cuts.

code-review-expert

Expert code review agent that performs systematic audits of git changes for SOLID violations, security vulnerabilities, performance regressions, and architectural smells.

langgraph

Expert LangGraph architect skill for designing stateful, multi-actor AI agent workflows with robust persistence, conditional branching, and ReAct patterns.