Skill UI

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

This skill details advanced techniques for enhancing the effective context capacity of LLMs. It outlines four core strategies—Compaction, Observation Masking, KV-Cache Optimization, and Context Partitioning—to prevent context limits from constraining task complexity. By strategically managing token usage, users can reduce operational costs, minimize latency, and implement robust, long-running agent systems for handling large documents or conversations.

A comprehensive pattern for building robust and cost-efficient LLM application pipelines. This guide details combining model routing based on task complexity, immutable cost tracking, limited retry logic, and prompt caching to manage API expenditures while maintaining high quality. Essential for production systems handling variable-complexity, high-volume tasks.

A comprehensive guide to optimizing LLM API usage within LangChain frameworks. Techniques include implementing token usage tracking, model tiering to route tasks based on complexity, utilizing caching to eliminate duplicate calls, prompt compression for efficiency, and enforcing strict budget limits to manage operational costs effectively.

A comprehensive checklist for ensuring LangChain applications are robust, secure, and scalable for production environments. It covers critical areas including configuration management, advanced error handling, observability setup (e.g., LangSmith), performance optimization, security best practices (like prompt injection prevention and PII handling), rigorous testing, and zero-downtime deployment strategies. Use this guide when preparing for a major launch or auditing existing LLM systems.

Learn how to monitor, analyze, and optimize the expenditure of Large Language Models (LLMs) using Langfuse's advanced analytics suite. This guide covers techniques like automatic token tracking, programmatic cost reporting via the Metrics API, and implementing smart model routing to automatically select the most cost-effective model based on task complexity and input length. Essential for any developer managing AI budgets and ensuring operational efficiency.

This skill simulates an expert prompt engineer, specializing in optimizing prompts for Large Language Models (LLMs). It applies advanced techniques such as Constitutional AI, Chain-of-Thought reasoning, and model-specific tuning. Use this tool to transform basic instructions into production-ready, high-performance prompts, significantly boosting accuracy, reducing hallucinations, and optimizing token usage.

High-performance RLHF framework that combines Ray, vLLM, and ZeRO-3 to accelerate PPO/GRPO/RLOO/DPO training for 7B-70B+ models on distributed GPU clusters, providing a single-stack workflow for reward models and policy optimization.

This skill provides comprehensive strategies for implementing robust caching mechanisms for OpenRouter API calls. It covers in-memory caching using Python, persistent caching with Redis for scalability, and utilizing provider-specific features like Anthropic prompt caching. By implementing deterministic key generation and managing Time-To-Live (TTL), developers can significantly reduce API costs and improve application latency when handling repetitive or similar LLM queries, making it ideal for RAG systems and high-volume applications.

This skill provides advanced strategies for managing large language model (LLM) context windows and token usage via OpenRouter. Functions include context window lookup, context-aware model selection, conversation trimming, document chunking for RAG, and prompt caching. Use this when dealing with long conversations or large documents to maximize quality while minimizing API costs and preventing context limit overflow.

This skill provides comprehensive methods for implementing intelligent model routing using the OpenRouter API. It allows developers to dynamically select the optimal Large Language Model (LLM) based on specific criteria: task complexity (e.g., classification, code generation), required capability (e.g., deep reasoning vs. simple Q&A), cost budget, and latency tolerance. Implement cost-aware, task-based, and complexity-based routing to maximize system efficiency and minimize operational expenses when building multi-model applications.