Fine-tunes TimeGPT on custom datasets to improve forecasting accuracy. Use when TimeGPT's zero-shot performance is insufficient or domain-specific accuracy is needed. Trigger with "finetune TimeGPT", "train TimeGPT", "adapt TimeGPT".
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
Run multiple AI models in parallel for 3-5x speedup with ENFORCED performance statistics tracking. Use when validating with Grok, Gemini, GPT-5, DeepSeek, or Claudish proxy for code review, consensus analysis, or multi-expert validation. NEW in v3.1.0 - SubagentStop hook enforces statistics collection, MANDATORY checklist prevents incomplete reviews, timing instrumentation examples. Includes dynamic model discovery via `claudish --top-models` and `claudish --free`, session-based workspaces, and Pattern 7-8 for tracking model performance. Trigger keywords - "grok", "gemini", "gpt-5", "deepseek", "claudish", "multiple models", "parallel review", "external AI", "consensus", "multi-model", "model performance", "statistics", "free models".
LLM fine-tuning and prompt-tuning techniques
Track traditional ML experiments in Domino using the MLflow-based Experiment Manager. Covers experiment setup, auto-logging for sklearn/TensorFlow/PyTorch, manual logging, artifact storage, run comparison, and model registration. Use when training ML models, logging metrics and parameters, comparing model runs, or registering models.
Provides industry-proven design patterns for effective AI agents based on production systems like Claude Code, Manus, and Cursor. Use when designing agent architectures, optimizing context management, or implementing sub-agent patterns.
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Build ML pipelines, experiment tracking, and model registries. Implements MLflow, Kubeflow, and automated retraining. Handles data versioning and reproducibility. Use PROACTIVELY for ML infrastructure, experiment management, or pipeline automation.
Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.
End-to-end AI system evaluation - model selection, benchmarks, cost/latency analysis, build vs buy decisions. Use when selecting models, designing eval pipelines, or making architecture decisions.
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
Expert in OCI Generative AI Dedicated AI Clusters - deployment, fine-tuning, optimization, and production operations
Analyze, compare, and work with tokenizers using Unsloth tools. Compare different tokenizers, analyze token efficiency, and integrate with Unsloth models. For SuperBPE training, see the 'superbpe' skill.
Query and analyze W&B experiment data and Weave LLM traces using Python scripts. Use when working with Weights & Biases data, including (1) querying ML experiment runs, metrics, and hyperparameters, (2) analyzing LLM traces and evaluations, (3) creating W&B reports, (4) listing projects and entities.
Execute Joseph Cognitive Baseline v2.1 evaluation protocol.
Implement ML pipelines, model serving, and feature engineering. Handles TensorFlow/PyTorch deployment, A/B testing, and monitoring. Use PROACTIVELY for ML model integration or production deployment.
Train task-specific small language models (SLMs) using the Distil Labs CLI. Helps with data preparation, model training, and deployment.
NVIDIA NIM inference microservices for deploying AI models with OpenAI-compatible APIs, self-hosted or cloud
Calculate training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "named entity recognition" (NER), "dependency parsing", "training TextCategorizer models", "troubleshooting spaCy errors" (E050/E941 model errors, E927 version mismatch, memory issues), "batch processing with nlp.pipe", or "deploying nlp models to production". Includes data preparation scripts, config templates, and FastAPI serving examples.
Optimize RAG performance with reranking, caching, parallel processing, and production deployment patterns. Use when improving retrieval quality, adding rerankers, deploying to production, implementing caching strategies, or optimizing for scale and latency.
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
