Analytics & Monitoring Agent Skills for VS Code

Azure Monitor OpenTelemetry Exporter for Java.

Automate Google Analytics tasks via Rube MCP (Composio): run reports, list accounts/properties, funnels, pivots, key events.

Detect quiet failures in LLM agents - tool skipping, gibberish outputs, infinite loops, and degraded quality.

Similarweb API for web analytics. Use when user mentions "Similarweb",

Logs and tracks the performance, satisfaction, and context of Claude Code skill executions for workflow optimization.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed…

Define Service Level Objectives (SLOs) and an error budget policy for a service.

Diagnoses breaching Grafana SLOs via gcx - root cause analysis, dimensional breakdown, alert rule correlation, runbook access.

Creates, updates, syncs, and deletes Grafana SLO definitions via gcx with dry-run validation and GitOps pull/push workflows.

Analyzes Grafana SLO timeline trends via gcx and produces data-backed advisory recommendations: objective tuning, alerting sensitivity…

Checks Grafana SLO health, error budget, and burn rate via gcx, with timeline graphs for trends.

Compact Snakemake workflow patterns. Keep rules short, complex logic in Python modules.

Social media monitoring, narrative tracking, and open-source intelligence for journalists.

Synchronizes implementation with intent by observing code changes against design specifications.

Bring declared user journeys within pre-declared performance budgets, proven by measurement.

This skill enables Claude to split datasets into training, validation, and testing sets.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers.

Analyze a startup from three perspectives: VC investor, job applicant, and CEO/founder.

Select an immediate HYROX pacing action from current HR, pace, breathing, fatigue, target pace, current station, and next demand.

Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes.

Show agent runtime status — identity, model, context, memory, crons, voice.