Agent Skills Hub

server-actions

Expert skill for Next.js Server Actions, covering form handling, data mutations, revalidation, and optimistic UI updates in the App Router.

agents

Build AI agents with tool calling and multi-step reasoning. Generate, manage, and orchestrate custom skill files for Claude Code, Cursor, Cline, and other AI assistants to standardize your development workflows.

serena-mcp

Semantic code analysis guide for Serena MCP. Automatically prioritizes Serena tools for symbols, references, and code memory to optimize context and efficiency.

aarnphm.github.io

A highly customized personal garden based on Quartz v4, featuring enhanced Markdown parsing, telescopic text, TikZ/pseudocode rendering, and Obsidian integration.

litestream

Expert technical support for the Litestream disaster recovery tool, covering WAL monitoring, LTX replication, cloud storage backends, and SQLite page management.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

performance-analysis

Systematic performance engineering: baseline measurement, profiling, bottleneck diagnosis, and evidence-based optimization guidance for high-performance applications.

code-quality

Enforce strict code quality, correctness, and Rust design patterns for the Turso database, prioritizing data integrity, performance, and maintainable, idiomatic code.

library

Private skill distribution system for managing agentics across devices and teams. Install, sync, add, and update your agents, skills, and prompts via a central library catalog.

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.

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.

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.