Skill catalog

Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated exper…

Debug a MAX model that loads, compiles, serves, and generates tokens but whose output disagrees with a reference implementation. Use whenever parity debugging stalls on scalar taps, the model returns gibberish or wrong…

Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

Bengali (Bangla) text processing patterns including Unicode normalization, script detection, tokenization, conjunct handling, and Bangla-specific NLP best practices for AI applications.

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision…

Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being ut…

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and prod…

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

Neural pattern training with SONA (Self-Optimizing Neural Architecture), MoE (Mixture of Experts), and EWC++ for knowledge consolidation. Use when: pattern learning, model optimization, knowledge transfer, adaptive rout…

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite.

Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial integration. If an experiment ID is available…

Create and manage Elastic ML anomaly detection jobs via the API. Use when setting up jobs on an index or data stream, configuring jobs and datafeeds, or opening, starting, or stopping them.

Explain Elasticsearch ML anomaly detection scores, model behavior, and result interpretation. Use when the user asks why a score is high or low, how the model learns, what the numbers mean, or how to troubleshoot unexpe…

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user menti…

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector…

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving model…

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or fo…

Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on…

Guides evaluation of RAG pipeline retrieval and generation quality. Use when evaluating a retrieval-augmented generation system, measuring retrieval quality, assessing generation faithfulness or relevance, generating sy…

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training…

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it…

Expert guidance for natural language processing development using transformers, spaCy, NLTK, and modern NLP techniques.