Analytics & Monitoring Agent Skills for Claude Code

Before any metric reaches a report, dashboard, exec deck, or stakeholder, name its population and definition, then adversarially re-query…

Investigate and diagnose issues without necessarily fixing them

Manage incident response workflow with Sentry alerts and issue tracking

Use when a European Economic Review (EER) manuscript needs a theoretical model built or tightened — a pure-theory result, a…

Analyze and optimize system throughput including request handling, data

Analyzes time-series data for patterns, trends, seasonality, and anomalies, with forecasting using statistical and machine learning methods.

Use this skill when the operator wants a prepared tmux visualization layout for the session's side-channels (STATE.md tail, CI-watch…

Together AI common errors for inference, fine-tuning, and model deployment.

Together AI cost tuning for inference, fine-tuning, and model deployment.

Together AI core workflow b for inference, fine-tuning, and model deployment.

Get current USD price for any token on Base via Birdeye (CoinGecko fallback).

Observability and reliability engineer — SLOs, alerting, instrumentation, and incident response.

ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook…

Use when analyzing conversation patterns — extracts dialog from Claude Code or Codex CLI history, classifies each user message across 6…

Use when context window is getting crowded, when dealing with long training logs, or when preparing prompts with mixed-priority content…

Audit event-emission posture (structured logging, metrics, trace propagation, event-schema consistency) in a target codebase

Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution.

Instrument LLM calls with tracing — span structure, token counts, latency, model metadata.

Audit LLM observability coverage — trace gaps, logging completeness, cost attribution accuracy.

Add W&B Models experiment tracking and guarded alerts to iterative experiment workflows, including Codex or Ralph-loop autoresearch.

Server-side analytics tracking with pluggable providers.