Agent Skills Hub

tools

Unified API for LLM function calling and tool use across OpenAI, Anthropic, Google, and Ollama with standardized schema definitions and execution patterns.

llm-integration

A toolkit for building robust LLM integrations: API patterns, streaming, function calling, RAG pipelines, and cost-effective model routing.

nexau-agent

Comprehensive guide and implementation framework for building, configuring, and deploying NexAU agents from scratch, including tools, prompts, and skills.

glyphbox

A framework for an LLM-based NetHack agent that dynamically synthesizes Python code in a secure sandbox to perform complex dungeon exploration and gameplay actions via a high-level API.

Delegating to AWS Agent

Implement an AI agent delegation architecture to keep your main context clean, reduce token costs, and isolate specialized infrastructure or API tasks.

qveris

Search and execute dynamic external tools via the QVeris API for real-time data retrieval, stock market analysis, and web-based tasks.

openai-agent-sdk-skill

Build AI agents, multi-agent systems, and workflows using the OpenAI Agents SDK for TypeScript/JavaScript. Supports tools, handoffs, guardrails, MCP, and realtime voice.

context-engineering-collection

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

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

saving-codeacts

Preserve successful Python code executions as reusable tools within the gentools package structure, utilizing Pydantic models for structured output and type-safe interfaces.

context-optimization

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

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.