Agent Skills Hub

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.

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.

basic-usage

Essential guide to llmemory for document storage and search: installation, database setup with pgvector, document ingestion, hybrid/semantic retrieval, and building RAG systems with multi-tenant support.

text-to-speech

Expert Kokoro TTS implementation skill for real-time, secure, and offline voice synthesis in JARVIS-style assistants. Features streaming output, prosody control, and performance-optimized audio generation.

test-delete-skill

Unified AI gateway for 100+ LLMs with OpenAI-compatible API, model fallbacks, load balancing, and enterprise-grade tools.

langgraph-workflows

Master multi-agent orchestration with LangGraph. Build stateful, fault-tolerant AI workflows using supervisor-worker patterns, conditional routing, and advanced state management.

openai-agents-sdk

Build AI agents with the OpenAI Agents SDK for Python. Supports multi-agent handoffs, function tools, stateful sessions, streaming, and Azure OpenAI integration via LiteLLM.

ocr

Extract text from images using the Tesseract OCR engine, supporting multiple languages, image preprocessing, and various formats.

nuwa-skill

A perspective engineering engine that researches, extracts mental models, and generates runnable persona skills based on deep expression DNA analysis.

plain-language

A toolkit for writing clear, accessible, and concise content. Applies Plain Language Movement principles including active voice, sentence shortening, and jargon elimination for improved reader comprehension.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

omc-plan

Intelligent strategic planning and requirements gathering with multi-perspective consensus loops and structured deliberation.