AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
frank-luongt Skill Multi Agent Patterns 5<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Autonomous Agent Patterns 4
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Agent Evaluation 4
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->
- frank-luongt Bundle Prompt Engineering Patterns 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Agent Tool Builder 4
<!-- AUTO-GENERATED by export-plugins.py — DO NOT EDIT -->
- frank-luongt Skill Autonomous Agent Patterns 5
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle LLM Application Dev AI Assistant 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle LLM Application Dev Langchain Agent 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle LLM Application Dev Prompt Optimize 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Multi Agent Patterns 4
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Huggingface Tokenizers 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Databricks Agent Bricks 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle MCP Enterprise Patterns 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Skill Agent Tool Builder 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Databricks Model Serving 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
- frank-luongt Bundle Autonomous Agent Patterns 3
<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->
-
j4flmao Bundle AI AgentsAI Agent Architectures
- j4flmao Bundle Ml Time Series
Use this skill when forecasting time series data, modeling trend/seasonality, applying ARIMA/SARIMA/Prophet/LSTM/TFT, or performing temporal cross-validation. This skill enforces: decomposition analysis (trend/seasonality/residual), stationarity testing, model selection by data characteristics, temporal cross-validation, forecast evaluation with MASE/sMAPE. Do NOT use for: generic regression on non-temporal data, anomaly detection in time series (use ml-anomaly-detection), causal inference with time series, or real-time streaming (use data-streaming skill).
- j4flmao Skill Genai Vision
Integrating Stable Diffusion for vision generation and Whisper for audio/multimodal tasks.
- j4flmao Skill LLM Finetuning
Best practices for dataset preparation and PEFT/LoRA fine-tuning.
- j4flmao Bundle Multi Agent Systems
Multi-Agent Systems (MAS)
- j4flmao Bundle Ml Experiment Tracking
Use this skill when asked about MLflow, W&B, Neptune, DVC, experiment tracking, run logging, metric logging, artifact store, model registry, hyperparameter logging, or experiment comparison. This skill enforces: experiment tracking platform setup (MLflow, W&B, Neptune), run logging conventions (params, metrics, artifacts), model registry versioning with stage promotion, experiment comparison using parallel coordinates, and full reproducibility through code + data + environment tracking. Do NOT use for: model training itself, feature engineering pipelines, or production deployment.
- j4flmao Bundle Ml Feature Engineering
Use this skill when asked about feature engineering, featuretools, tsfresh, feature selection, feature extraction, encoding, scaling, one-hot encoding, target encoding, feature interaction, datetime features, text features, or feature importance. This skill enforces: categorical encoding strategies (one-hot, label, target, ordinal), numerical scaling methods (standard, min-max, robust), datetime feature extraction (year, month, day, dayofweek, cyclical encoding), text feature extraction (TF-IDF, count vectorizer, word embeddings), feature interaction generation, feature selection techniques (filter, wrapper, embedded), and automated feature engineering with Featuretools deep feature synthesis and tsfresh for time-series. Do NOT use for: model training, deep learning architecture, or experiment tracking.
- j4flmao Bundle Mobile Ar Vr
Use this skill when the user says 'AR', 'VR', 'augmented reality', 'virtual reality', 'ARKit', 'ARCore', 'Unity AR', '3D rendering', 'SceneView', 'AR scene', 'AR interaction', 'AR performance'. This skill enforces: platform-specific AR configuration (ARKit vs ARCore), scene setup with anchor management, optimal 3D model handling with LODs and compression, interaction patterns for gesture and placement, performance budgets (<60fps, <200MB), and VR integration considerations. Do NOT use for: general mobile UI/UX design, game engine tutorials unrelated to AR/VR, or 3D modeling software usage instructions.
- j4flmao Bundle Ml Hyperparameter Tuning
Use this skill when performing hyperparameter tuning, optimizing model performance via search strategies, or configuring tuning frameworks (Optuna, Ray Tune, Hyperopt). This skill enforces: search space definition, strategy selection (grid/random/Bayesian), framework configuration, pruning/early stopping, distributed execution, multi-objective optimization. Do NOT use for: model architecture search (NAS), feature selection, threshold tuning for classification, experiment tracking (use ml-experiment-tracking).
- j4flmao Bundle Product Pricing Strategy
Use this skill when defining pricing strategy: value metrics, pricing models, packaging tiers, and pricing page experimentation. This skill enforces: value metric identification, pricing model selection, packaging design, willingness-to-pay research. Do NOT use for: discounting strategy, enterprise sales negotiation, contract management, revenue recognition.
- j4flmao Skill Inference Optimization
LLM Inference Optimization & MLOps
- j4flmao Bundle Ml Model Interpretability
Use this skill when explaining model predictions, computing feature importance, generating SHAP/LIME explanations, creating dependence plots, or building trust in ML model decisions. This skill enforces: global + local explanation coverage, SHAP value computation, permutation importance baseline, visualization choice (waterfall/force/dependence/summary), model-specific methods, feature interaction detection. Do NOT use for: model evaluation metrics (use ml-model-evaluation), hyperparameter tuning (use ml-hyperparameter-tuning), causal inference, or privacy-preserving explanations.
- j4flmao Skill AI Agent Memory Paradigms
Theoretical foundations of Working, Semantic, and Episodic memory systems for autonomous agents.
- j4flmao Skill Kv Cache
KV Cache and Attention Mechanisms: PagedAttention and vLLM
- j4flmao Bundle Agent Observability
Comprehensive skill for tracing reasoning paths, debugging non-deterministic agent loops, and monitoring agent behavior in production systems. Covers reasoning trace visualization, OpenTelemetry integration for agent systems, distributed tracing across multi-agent chains, decision audit logging, performance profiling, anomaly detection, cost tracking and optimization, and latency analysis for AI agent deployments.
- j4flmao Skill Fundamental Truth Statistical Mechanics Diffusion
The thermodynamic and statistical mechanical basis of generative intelligence. Langevin dynamics, SDEs, and the physics of the forward/reverse noise processes.
- j4flmao Skill Tensorrt Optimization
Authoritative guide to inference optimization using TensorRT, focusing on quantization, layer fusion, and memory bandwidth optimization for LLMs.
- j4flmao Bundle Data Graph Database
Use this skill when asked about Neo4j, Amazon Neptune, JanusGraph, graph database, graph model, Cypher, Gremlin, RDF, SPARQL, graph traversal, property graph, or knowledge graph. This skill enforces: graph data modeling (property graph, RDF), Neo4j/Cypher query patterns, Amazon Neptune/Gremlin traversal, JanusGraph architecture with backend storage, graph traversal optimization, knowledge graph design for connected domains, and performance tuning (indexing, caching, query planning). Do NOT use for: document storage, wide-column time-series, or full-text search.
- j4flmao Bundle Ml Model Evaluation
Use this skill when evaluating model performance, selecting metrics, designing cross-validation strategies, diagnosing bias-variance tradeoffs, or performing statistical significance testing. This skill enforces: metric selection by task type, cross-validation strategy by data structure, bias-variance diagnosis, learning curve analysis, statistical significance protocol. Do NOT use for: hyperparameter tuning (use ml-hyperparameter-tuning), experiment tracking (use ml-experiment-tracking), model explainability (use ml-model-interpretability).
- j4flmao Bundle Quality E2e Testing
Use this skill when setting up E2E testing, end-to-end tests, Playwright, Cypress, browser tests, user flow tests, or integration tests. This skill enforces: framework selection (Playwright preferred), page object model, test isolation, parallel execution, CI integration, and visual assertions. Do NOT use for: unit testing, API-only tests, or performance/load testing.
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include multi-agent-patterns, autonomous-agent-patterns, agent-evaluation. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.