Ai Ml skills for AI agents
10 practitioner-grade ai ml skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 10 skills
- Computer Vision Pipeline
Designing computer vision pipelines for image and video analysis tasks. Covers classification, object detection, segmentation, data augmentation, and model optimization. Trigger keywords: computer vision, image classification, object detection, segmentation, image processing, CNN, vision transformer.
144 lines - Data Preprocessing
Systematic approach to data cleaning, transformation, and feature preparation for machine learning. Covers missing values, encoding, scaling, outlier handling, and feature engineering. Trigger keywords: data cleaning, preprocessing, feature engineering, data preparation, ETL for ML.
158 lines - ML Deployment
ML model deployment and MLOps practices for production systems. Covers serving infrastructure, model versioning, monitoring, CI/CD for ML, and A/B testing. Trigger keywords: ML deployment, MLOps, model serving, production ML, model monitoring, ML pipeline, model registry.
91 lines - ML Evaluation
Comprehensive model evaluation and metrics selection for machine learning. Covers classification, regression, ranking metrics, cross-validation strategies, and statistical testing. Trigger keywords: model evaluation, metrics, accuracy, F1 score, AUC, cross-validation, model comparison.
96 lines - ML Model Selection
Guides you through choosing the right machine learning model for a given problem. Covers supervised, unsupervised, and reinforcement learning paradigms with decision criteria based on data characteristics, performance requirements, and constraints. Trigger keywords: model selection, algorithm choice, ML approach, which model.
136 lines - Neural Network Architecture
Guides the design of neural network architectures for various tasks. Covers layer selection, depth/width tradeoffs, activation functions, regularization, and modern architecture patterns. Trigger keywords: neural network design, deep learning architecture, CNN, transformer, network topology.
89 lines - Nlp Pipeline
Designing end-to-end natural language processing pipelines from text ingestion to model serving. Covers tokenization, embeddings, transformer models, and task-specific architectures. Trigger keywords: NLP pipeline, text processing, language model, text classification, NER, sentiment analysis.
90 lines - Prompt Engineering
Advanced prompt engineering techniques for large language models. Covers structured prompting, chain-of-thought, few-shot examples, system prompts, and output control. Trigger keywords: prompt design, LLM prompting, prompt optimization, prompt template.
155 lines - Reinforcement Learning
Guide for reinforcement learning systems where agents learn through environment interaction and reward signals. Use when designing RL pipelines, selecting algorithms, or building reward functions. Trigger keywords: reinforcement learning, RL, reward shaping, policy gradient, Q-learning, multi-armed bandit, MDP.
83 lines - Time Series Forecasting
Techniques for predicting future values from sequential temporal data. Use when building forecasting models, analyzing trends, or handling seasonality. Trigger keywords: time series, forecasting, ARIMA, prophet, seasonal decomposition, trend analysis, temporal prediction.
81 lines