Analytics & Monitoring Agent Skills for Codex CLI

Use when formulating the model and stating results for an Operations Research (OR) manuscript — defining the…

Refresh a user- or project-owned point-in-time guide for model prompting, benchmark-aware routing, execution lanes, and pricing when the…

Generate a reproducible, runnable PyTorch training repo for a medical-imaging task — segmentation, classification, detection…

When to activate: model serving, inference, FastAPI ML, BentoML, Triton, vLLM, model deployment, online inference, batching

Vet the concrete third-party model a study will be built on — this repository, this revision, this checkpoint — not the architecture family.

Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.

Use sd-scripts model and network utilities safely: LoRA

Design or audit the clinical-validation study for an engineer-built medical-imaging model (segmentation, classification, or detection)…

Use when explaining heterogeneity and probing robustness in a Psychological Bulletin meta-analysis — moderator/subgroup analysis…

Two-window momentum analysis for any topic: run last30days once (30-day sweep), immediately re-score the same corpus under a shorter…

Monitor running experiments, check progress, collect results.

This skill enables Claude to monitor and analyze CPU usage patterns within applications.

This skill enables Claude to monitor and analyze application error rates to improve reliability.

Configures monitoring systems, implements structured logging pipelines, creates Prometheus/Grafana dashboards, defines alerting rules, and…

When to activate: monitoring, observability, SLO, SLI, SLA, alerting, dashboard, Prometheus, Grafana, Alertmanager, uptime, latency

Define monitoring strategy, metrics collection, and alerting thresholds during PRD v0.8 Deployment & Ops.

Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production.

Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production.

Track large cryptocurrency transactions and whale wallet movements in

Triage Monte Carlo alerts interactively or build an automated workflow.

Generate SQL validation notebooks for dbt changes.