Analytics & Monitoring Agent Skills for OpenAI Agents SDK

Guide for working with Splitrail's MCP server.

Use before modifying, refactoring, or deleting files in a codebase that has Repowise indexed (indicated by a .repowise/ directory).

Search and analyze your own session logs (older/parent conversations) using jq.

Analyzes Claude Code Skill usage logs to generate performance reports, satisfaction trends, and optimization insights.

Audit token usage patterns — avg context size, waste, truncation frequency, budget adherence.

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph…

Identify anomalous sessions using Agent Monitor data — cost outliers from the pricing engine, token anomalies (cache miss spikes…

Generate ASCII mini charts (sparkline/bar/simple line) for plain-text trend inspection, with minimal + annotated variants and…

Generates Correlation ID propagation components for PHP 8.4.

Add Vercel Analytics, Vercel Speed Insights, and Google Tag Manager to the storefront.

Pull metrics from analytics dashboards and internal web tools with Firecrawl browser.

Generate MSBuild binary logs (binlogs) for build diagnostics and analysis.

Compare GWAS studies, perform meta-analyses across cohorts, and assess signal replication.

Define UX metrics and KPIs that connect design decisions to measurable outcomes.

Master context engineering for AI agent systems.

Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health.

Investigate a network incident by correlating device events with camera footage and physical access logs.

Provides guidance on using the next-devtools MCP server.

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns.

Analyze SaaS company valuation compression between funding rounds.