Agent Skills Hub

llm-integration

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

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.

project-development

A framework for managing the end-to-end LLM project lifecycle, from evaluating task-model fit and pipeline architecture design to implementing structured output parsing and agent-assisted development.

prompt-optimizer

Transforms vague or poorly structured prompts into optimized, high-performance instructions using proven prompt engineering principles for better AI model execution.

mcp-development

Guidance for Model Context Protocol (MCP) server development, including tool design, resource handling, and AI/ML integration patterns.

llmintegration

Multi-model LLM integration patterns for Claude, GPT, Gemini, and Ollama. Features API handling, prompt engineering, token management, and model-agnostic orchestration.

moollm

A microworld operating system for LLM-based agent living memory, transforming filesystems into navigable rooms and code into habitable worlds.

test-delete-skill

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

context-engineering-collection

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

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

tools

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

opper-api

Direct access to the Opper REST API for LLM orchestration, model management, task execution, and seamless migration from OpenAI, Anthropic, or OpenRouter.