Analytics & Monitoring Agent Skills for Claude Code

Use when generating performance hypotheses backed by git history and code evidence.

Validate application performance against defined budgets to identify

Expert performance engineer specializing in modern observability,

Use for performance optimization, performance regression analysis, throughput, latency, memory, CPU, allocation, IO, concurrency…

Use when the computational exhibits — performance profiles, runtime-vs-size plots, and results tables — are dense, misleading, or do not…

Investigate performance regressions and find opportunities for optimization

Provide comprehensive prioritized performance optimization recommendations

Identifies and fixes performance bottlenecks in code, databases, and APIs.

Performance profiling principles. Measurement, analysis, and optimization techniques.

Performance profiling and bottleneck detection for Node.js, Python, and browser apps

Install the active skill from the bundle: Full 20 → 16 mapping: see the repo README.

This skill empowers Claude to perform regression analysis and modeling using the regression-analysis-tool plugin.

Apply Perplexity advanced debugging techniques for hard-to-diagnose issues.

Optimize Perplexity costs through tier selection, sampling, and usage monitoring.

Collect Perplexity debug evidence for support tickets and troubleshooting.

Execute Perplexity incident response procedures with triage, mitigation, and postmortem.

Set up comprehensive observability for Perplexity integrations with metrics, traces, and alerts.

Collect Persona diagnostic info: inquiry IDs, API responses, webhook

Phase 3 of building a Claude Managed Agent — the bounded grade→iterate loop.

Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with…

Generates onboarding code snippets for Phoenix tracing integrations and wires them into the project onboarding UI.