Skill UI

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

Provides automated guidance for setting up canary deployments in ML production environments, covering model serving, MLOps pipelines, monitoring, and configuration validation.

Automated guidance for batch request handler tasks inside API integration workflows, covering best practices, code generation, webhook patterns, and validations when dealing with third-party APIs.

Automated GCP skill that activates when you ask about BigQuery ML model creator tasks, delivering best-practice guidance, production-ready code, and validation for compute, storage, BigQuery, Vertex AI, and other platform services.

This skill serves as a comprehensive health assistant, designed to analyze complex medical information, track symptoms over time, and provide personalized wellness guidance. It is useful for users seeking structured health monitoring and preliminary insights into their condition, but it must not replace professional medical diagnosis or advice.

Provides expert guidance on designing, implementing, and optimizing cutting-edge computer vision pipelines. Expertise spans real-time object detection (YOLO26), advanced promptable segmentation (SAM 3), and leveraging Vision Language Models (VLMs) for complex visual reasoning. Ideal for building high-performance systems in robotics, autonomous vehicles, and industrial inspection, including 3D reconstruction and edge deployment optimization.

Assists ML Training workflows by automatically activating on confusion matrix generator requests, offering structured guidance, best-practice checks, and ready-to-use code snippets.

Automates dataset loader creation within ML Training workflows, offering best-practice guidance, validation checks, and production-ready code to accelerate data prep and model tuning.

Provides comprehensive guidance on building robust evaluation frameworks for complex agent systems. It addresses the inherent challenges of non-determinism and multiple valid paths, enabling systematic performance testing, validating context engineering choices, and measuring continuous improvements across multiple quality dimensions (e.g., factual accuracy, tool efficiency).

Automatically activates when you mention feature engineering helper, offering guidance on data preparation, model training, hyperparameter tuning, and experiment tracking for ML projects.

Provides expert guidance for GRPO training with TRL, covering dataset prep, reward engineering, structured outputs, and multi-objective alignment when preference pairs are scarce.