Analytics & Monitoring Agent Skills for Claude Desktop

ML reconnaissance — inventory all models, pipelines, data sources, and monitoring.

ML optimization sweet spot principle: "More is not always better".

When to activate: MLflow, experiment tracking, model registry, autologging, MLflow serving, artifact storage, model signatures, ML lifecycle

Show the current MLflow tracing configuration for Claude Code.

Design or audit a model-agnostic evaluation harness for an LLM or multimodal LLM on a clinical task (radiology report generation, visual…

MLOps and Platform: 23 concepts, no maths assumed.

When to activate: MLOps, DVC, model versioning, drift detection, Evidently, WhyLogs, retraining, ML CI/CD, model monitoring

Use when packaging an accepted MLSys paper's code, configs, and measurement scripts for the venue's post-acceptance artifact evaluation…

Use when deciding whether a project belongs at MLSys rather than OSDI, SOSP, NSDI, ASPLOS, ATC, EuroSys, or the ML conferences, testing…

Analyze AI disruption pressure across a business, map competitive exposure, and produce a 90-day defensive action plan.

Choose an ML model or provider when a user asks which checkpoint, router, local model, adapter, tokenizer, or inference backend fits a…

Deploy this skill enables AI assistant to deploy machine learning models

Avoid ensembling models with significantly different performance.

Measure which capability tier a model can be trusted with and where its reasoning budget stops paying, then write it into the…

Save, load, inspect, minify, and share scvi-tools model artifacts

Use when building the formal model for a Marketing Science manuscript — turning a marketing phenomenon into an analytical (game-theoretic)…

Use when formulating the model and stating results for an Operations Research (OR) manuscript — defining the…

Refresh a user- or project-owned point-in-time guide for model prompting, benchmark-aware routing, execution lanes, and pricing when the…

Generate a reproducible, runnable PyTorch training repo for a medical-imaging task — segmentation, classification, detection…

When to activate: model serving, inference, FastAPI ML, BentoML, Triton, vLLM, model deployment, online inference, batching

Vet the concrete third-party model a study will be built on — this repository, this revision, this checkpoint — not the architecture family.