Analytics & Monitoring Agent Skills for ChatGPT

Pyodide WASM apps in Web Workers. Use for Python-in-browser.

Profile the execution time of a Python script using py-spy and visualize the result with speedscope.

When to activate: ETL, data pipeline, Prefect, Airflow, DLT, Polars, batch processing, data quality

Python patterns for system reliability — background jobs and task queues (Celery, async), resilience and recovery (retries, backoff…

When to activate: Python logging, structlog, JSON logs, correlation IDs, log levels, observability setup

When to activate: scikit-learn, machine learning pipelines, feature engineering, model evaluation, cross-validation

When to activate: OpenTelemetry, traces, metrics, spans, Prometheus, Grafana, Sentry, APM setup

When to activate: Python profiling, cProfile, memory profiling, optimization, numba, Cython, bottlenecks

Fully sharded data-parallel training for large models.

When to activate: PyTorch, nn.Module, DataLoader, training loop, mixed precision, DDP, distributed training, torch.compile, model export…

Tracks quality metrics including defect density, test effectiveness ratio, DORA metrics, and mean time to detection.

Design, select, critique, and revise quantitative data visualizations for accurate, efficient human perception.

One-line summary of key Agent Monitor metrics — active sessions, total cost from the pricing engine, events today from daily_events, top…

Fast vibration health screening for industrial machinery using the predictive-maintenance-mcp server.

Agent-only decision procedure for resolving a matched crew-dispatch profile array from current quota-axi output, including effective…

Track Claude Code quota usage via Anthropic API rate limit headers.

Create, update, review, and test production-quality R scripts for data ingest, cleaning, transformation, analysis, visualization…

Produce or audit a radiomics / tabular clinical-ML study — imaging or clinical features → any classical learner (penalised logistic [LASSO…

Retrieval-Augmented Generation patterns for grounded LLM responses.

When to activate: RAG, retrieval augmented generation, LangChain, LlamaIndex, vector stores, embeddings, retrieval, chunking, reranking…