ai-engineering-os

Walks a student through designing a complete 5-layer intelligent system for any real business problem. Use this skill whenever a student wants to go beyond building a model and design the full system around it — the decision layer, the policy, the action layer, and the feedback loop. Trigger this skill when the user says things like "design an agentic system for [problem]", "help me build the 5 layers for [problem]", "how do I connect my ML model to actual actions", "design the decision layer for my [model]", "build a policy for [prediction output]", "how do I close the feedback loop for [system]", "design the full pipeline for [business problem]", or any request to turn an ML prediction into a working intelligent system. Works with output from any ML model — supervised predictions, unsupervised cluster assignments, anomaly scores, or any other model output. This skill is the bridge between "I built a model" and "I deployed a system that changes outcomes." Always use this skill when a student has an ML output

Generates a complete thinking document for any unsupervised ML algorithm in the exact style and depth of the Session 2 "Unsupervised Learning + K-Means" teaching document. Use this skill whenever a student wants to deeply understand an unsupervised ML algorithm — not just its mechanics but the full strategic thinking behind it: the framing shift from supervised to unsupervised, hypothesis about data shape, loss equivalent and what it actually measures, optimization without gradient descent, evaluation without ground truth, and how to connect the algorithm's output to the 5-layer agentic system stack. Trigger this skill when the user says things like "help me understand [algorithm] the way we did K-Means", "build a thinking doc for [unsupervised algorithm]", "apply the 10 frameworks to [algorithm]", "walk me through DBSCAN / PCA / hierarchical clustering / GMM / UMAP / isolation forest like session 2 taught K-Means", or any request to deeply understand an unsupervised learning algorithm from first principles.

Generates a complete thinking document for any supervised ML algorithm in the exact style of the "Regression & Supervised Learning: The Evolutionary Thinking Framework" session document. Use this skill whenever a student wants to deeply understand a supervised ML algorithm — not just its mechanics but the full strategic thinking behind it: problem framing, hypothesis choice, loss function as a business decision, optimization failure modes, feature engineering, regularization, leakage, assumption diagnostics, and agent orchestration moments. Trigger this skill when the user says things like "help me understand [algorithm] the way we did regression", "build a thinking doc for [algorithm]", "apply the 13 frameworks to [algorithm]", "walk me through [algorithm] like the session", or any request to deeply understand a supervised learning algorithm from first principles using the evolutionary thinking approach. This skill works for ANY supervised learning algorithm — logistic regression, decision trees, random fore