Skill UI

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.

This toolkit provides a comprehensive framework for managing and optimizing API costs when using Mistral AI. It includes functions for calculating token-based costs across various models, implementing a smart model router based on task complexity, and managing daily/monthly budgets with critical alerts. Furthermore, it offers methods for prompt optimization to reduce token consumption, making it essential for large-scale application cost control and billing analysis.

This guide provides advanced techniques for optimizing Mistral AI API usage, focusing on latency reduction and throughput maximization. Learn to implement robust caching strategies, utilize streaming responses (SSE), select the optimal model for specific use cases (e.g., Mistral Small for chat, Codestral for code), manage concurrent requests using rate limiting, and efficiently use the Batch API. Essential for building high-performance, production-grade AI applications.

Automates mixed precision ML training workflows by surfacing best practices, generating runnable code/configurations, and validating setups across data prep, model tuning, and experiment tracking.

This skill provides comprehensive best practices and Python code examples for optimizing API calls to Large Language Models (LLMs) via OpenRouter. It covers benchmarking model latency, implementing streaming to achieve low Time-To-First-Token (TTFT), and processing requests concurrently using asynchronous programming (asyncio). Use this when developing real-time, high-throughput applications that require predictable and fast model responses.

Auto-activating ML training skill that kicks in whenever you mention optuna study creator, then guides you through data prep, model training, hyperparameter tuning, and experiment tracking with production-ready code and validations.

This guide provides advanced strategies for developers to significantly reduce Perplexity Sonar API billing costs. It covers key techniques including model routing (selecting the right model by query type), setting maximum output tokens, implementing robust query caching, and utilizing domain filters to minimize per-request charges. Essential for building cost-effective, high-volume AI applications.

This guide provides advanced architectural patterns to optimize interactions with the Perplexity Sonar API. By implementing smart model routing, query hashing with time-to-live (TTL) caching, streaming responses, and rate-limited parallel processing, developers can significantly reduce latency, improve overall throughput, and manage API costs. Ideal for integrating complex, research-intensive search-augmented applications.

Automates PyTorch training workflows by guiding data preparation, model configuration, hyperparameter tuning, and experiment tracking while following industry best practices for production readiness.

Quantizes HuggingFace LLMs to 8-bit or 4-bit with bitsandbytes, cutting memory by up to 75% while keeping accuracy, and supports QLoRA fine-tuning plus 8-bit optimizers for faster, memory-efficient training.

Automates ROC curve plotting tasks in ML training, guiding data prep, model training, tuning, tracking, and code generation for production-ready results.

SimPO (Simple Preference Optimization) is a state-of-the-art, reference-free method designed for aligning Large Language Models (LLMs) using human preference data. It is an efficient alternative to DPO and PPO, notably outperforming DPO without requiring a separate reference model. It is ideal for practitioners who need faster, simpler, and more resource-efficient fine-tuning for preference alignment.