Analytics & Monitoring Agent Skills

Collect Databricks debug evidence for support tickets and troubleshooting.

Create a minimal working Databricks example with cluster and notebook.

Ports existing Databricks notebooks and jobs to Fabric, covering dbutils to notebookutils, secret scopes to Key Vault, DBFS to OneLake…

Guides developers building Datadog Apps with TypeScript, React, the @datadog/apps scaffolder, and @datadog/vite-plugin.

Datadog Browser SDK — RUM, Logs, Session Replay, profiling, product analytics, and error tracking setup, configuration, and migration.

Set up the Datadog Google Cloud integration with Terraform - creates a service account in the host project, lets Datadog's delegate…

Generate a Datadog dashboard JSON to monitor a user lifecycle (funnel, workflow, or adoption cohorts) for a customers-backend…

Recommends the right Datadog products for a codebase and/or a stated goal — grounded in a tech-stack→product map and a use-case→product…

Use this skill when the user wants to manage data quality in DataHub: create or run assertions, check assertion outcomes, raise or resolve…

Prepare, format, and validate datasets for supervised fine-tuning and preference training.

Process split datasets into training, validation, and testing sets for

Automate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries.

Automate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call rotations.

Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations.

Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations.

Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction

You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools.

Troubleshoot Coval OpenTelemetry trace ingestion, missing trace UI, sparse traces, bad simulation or conversation correlation, auth/org…

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

Add purposeful debug logging to improve observability without changing behavior.

Use when the user asks to debug, check, or diagnose a Snakemake pipeline on a remote cluster.