Skill UI

This comprehensive guide helps developers safely migrate between different versions of the Kling AI video generation model (e.g., v1.x to v2.x). It details breaking changes, parameter differences, feature availability matrices (including native audio and camera control), and provides code examples for parallel A/B testing and robust rollback strategies, ensuring seamless API adoption.

Integrate Langfuse into CI/CD pipelines (e.g., GitHub Actions) to automate the testing and validation of Large Language Models (LLMs). This guide covers prompt regression testing, tracing validation, and setting up experiment-driven quality gates, ensuring reliable and high-performing AI applications throughout the development lifecycle.

Master comprehensive strategies for evaluating Large Language Model (LLM) applications. This skill covers automated metrics (BLEU, ROUGE, BERTScore), structured human evaluation dimensions, and advanced LLM-as-Judge techniques. Use it to systematically measure model performance, compare prompts, detect regressions, and build confidence in production systems.

Automate the validation and testing of prompts and AI responses within your CI/CD pipeline using Mistral AI. This integration provides robust prompt regression testing, model quality checks, automatic cost estimation for API usage, and deployment gates, ensuring the stability and reliability of your AI features upon every pull request.

A comprehensive skill set for building, deploying, and managing production-grade Machine Learning systems. Expertise spans modern frameworks (PyTorch, TensorFlow), model serving using Kubernetes, advanced feature engineering (Feast, Tecton), and robust MLOps practices (monitoring, A/B testing, CI/CD). Focuses on delivering scalable, reliable, and business-value-driven AI solutions.

This skill provides comprehensive guidance for building production-grade MLOps pipelines. It covers the entire machine learning lifecycle, from initial data ingestion and rigorous feature engineering to model training, advanced validation (A/B testing, performance drift), and robust deployment strategies (Canary, Blue-green). It enables the design and orchestration of scalable, reproducible, and observable ML systems using tools like Airflow and Kubeflow.

This guide provides a comprehensive quickstart for integrating with OpenRouter, a unified endpoint for accessing multiple large language models (LLMs). It includes examples in cURL, Python, and TypeScript, demonstrating how to send chat completion requests, handle complex JSON responses, manage model parameters, and calculate usage cost across various providers (e.g., Llama, GPT-4o, Claude). Ideal for developers testing API connectivity or building multi-model applications.

This skill is designed for running comprehensive evaluations of Hugging Face Hub models on local hardware. It supports multiple evaluation frameworks, including `inspect-ai` and `lighteval`, and provides flexibility in backend selection (e.g., `vllm`, Transformers, or `accelerate`) to optimize for performance and compatibility. Use this for local GPU benchmarking, smoke testing, and backend selection, but note that it does not handle remote job orchestration or result publishing.

Phoenix Evals enables developers to build and run evaluators for AI and LLM applications. It supports both code-based and LLM-based evaluation methods, including RAG systems. Users can create datasets, run experiments, validate evaluator accuracy, and implement production guardrails. Available in Python and TypeScript, it helps ensure model performance and reliability through systematic testing and human validation.

Automates comprehensive regression testing for all enabled cloud Large Language Model (LLM) providers. This includes verifying core connectivity, standard chat completion, structured JSON output, and Server-Sent Events (SSE) streaming capabilities. Essential for ensuring the reliability and stability of multi-cloud AI integrations in a CI/CD pipeline.

This harness provides comprehensive, reproducible evaluation pipelines for complex LLM chains and agents (LangChain/LangGraph 1.0). It integrates golden dataset management, LangSmith evaluation, RAGAS metrics, deepeval LLM-as-judge, and structured agent trajectory analysis. Use it when establishing quality benchmarks for new chains, diagnosing performance regressions after model switches, or implementing CI/CD gates to prevent quality drops.

This comprehensive benchmark suite evaluates the performance of Vision-Language Models (VLM) on complex video anomaly detection tasks using the SmartHome-Bench dataset. It covers a wide range of real-world smart home scenarios, including security breaches, elderly fall detection, and unusual pet behavior. Unlike single-frame analysis, this benchmark requires deep multi-frame video understanding, making it a robust tool for testing the advanced AI capabilities of video monitoring systems.