ayush488-glitch

Anti-slop agentic engineering co-pilot. Teaches the Research-Plan-Implement (RPI) workflow, context management, quality gates, per-agent isolation, and anti-slop patterns for building software with AI coding agents. Produces agent-workflow.md or project configuration files. Part of the mlops-tabular skill family but independently invocable for any software project.

Full software engineering and ML-specific code review co-pilot. Reviews Python code for quality, security, testing, type safety, and ML-specific issues including data leakage, training-serving skew, feature engineering smells, and reproducibility. Produces structured review findings by severity. Part of the mlops-tabular skill family. Invoke via /mlops-tabular or directly for any Python/ML code review.

System design co-pilot covering both general distributed systems and ML-specific infrastructure. Guides users through API design, database design, scalability, reliability, ML serving patterns, feature stores, training pipelines, and ML platform architecture. Produces system_design.md. Part of the mlops-tabular skill family. Invoke via /mlops-tabular or directly for any system design problem.

Production-grade MLOps co-pilot for tabular data. Guides users end-to-end from business problem through system design, implementation, deployment, and monitoring. Adapts dynamically to the user's specific problem, dataset, constraints, and chosen orchestration framework. Use when asked to build an ML product on tabular data, productionize a model, set up MLOps infrastructure, or when users describe a business problem they want to solve with machine learning on structured data. Proactively invoke when: user describes a business problem solvable with tabular ML, mentions prediction/classification/regression on structured data, or asks about MLOps best practices for a specific project.

Deep-dive MLOps architecture design for tabular data. Walks through all 9 sub-phases of system design: full pipeline explanation (10 stages, 5 pipelines, maturity levels), data plan, feature plan, training plan, deployment plan, monitoring plan, versioning plan, ZenML stack selection, and architecture document production. Reads problem_statement.md, produces architecture.md. Part of the mlops-tabular skill family.

Deep-dive data foundation and feature engineering for tabular ML. Covers project setup, data loading with validation, EDA, and preprocessing (null handling, scaling with formulas, categorical encoding with target encoding smoothing, training-serving skew prevention with sklearn.Pipeline). Reads problem_statement.md and architecture.md. Part of the mlops-tabular skill family.

Deep-dive deployment, monitoring, and production hardening for tabular ML. Covers drift detection (data vs concept drift, KS/Chi-squared/PSI/Wasserstein with thresholds), deployment strategies (shadow/canary/blue-green/A-B), four-layer monitoring ladder, incident response, feedback loop dangers, production hardening, and shipping. Part of the mlops-tabular skill family.

Deep-dive problem framing for tabular ML. Guides users through the six-word ML suitability test, three legitimate paths (Build ML / Rules / Not Now), problem statement template, metric ladder, seven discovery questions, and six forcing questions. Produces problem_statement.md. Part of the mlops-tabular skill family. Invoke via /mlops-tabular or directly when you need focused problem framing.

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

Personalized 6-month action plan to land a $100K AI job or equivalent income. Runs a 3-round intake (15 questions), then generates a fully personalized plan covering: architecture learning roadmap, skill value audit, 10 LinkedIn post drafts, outreach templates, research paper reading list, and a week-by-week 6-month timeline. Built by Ayush Singh / Second Brain Labs.