Analytics & Monitoring Agent Skills for Claude Code

Set up comprehensive observability for Databricks with metrics, traces, and alerts.

Automate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes.

Pythonic wrapper around RDKit with simplified interface and sensible defaults.

Generates code that transforms datasets between ML schemas for model training or evaluation.

Discover what datasources, metrics, labels, and log streams are available in a Grafana instance.

Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification.

DAX performance optimization for semantic models.

Gathers the data an engineer needs to remediate a partnerships DDC (Declarative Data Check) failure: fetches the check config, locates the…

Automated covenant compliance monitoring and calculation skill with early warning alerts

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools.

Debug and troubleshoot production issues on Azure.

Debug, support, and build PostHog Surveys across the backend and all five SDKs (web/posthog-js, iOS, Android, Flutter, React Native).

Debug the signals pipeline locally end-to-end.

Decision-specific visualization skill for creating clear, actionable visual representations of analyses

Query DeepSeek Open Platform account balance.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam…

NVIDIA DeepStream SDK development with Python pyservicemaker API.

Build DeepStream GStreamer pipelines interactively.

Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a…

This skill enables Claude to deploy machine learning models to production environments.