Analytics & Monitoring Agent Skills

Root cause analysis for bugs, failures, regressions, incidents, broken flows, failing tests/builds/CI, production errors, or odd behavior.

Use when designing or auditing the experimental campaign for an RSS (Robotics: Science and Systems) paper — hypothesis-shaped robot…

Read The Fucking Prompt — finds the strongest user reaction to an AI instruction-following failure in a chosen session, reconstructs what…

When to activate: Ruby performance, rack-mini-profiler, stackprof, fragment caching, Marshal serialization, GC tuning, memoization, Rails…

Standardizes the creation, maintenance, and drilling of operational runbooks to ensure system reliability and incident response readiness.

Performance regression gate. Detects N+1 queries, sync-in-async, missing indexes, memory leaks, and bundle bloat before they reach…

Engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with trend tracking. Per-person breakdowns…

Use when getting research work running on the lab's `sprc` cluster, including deciding whether light work belongs on the host `sprlab005`…

Use when querying CMF metadata programmatically — listing pipelines, stages, executions, artifacts; tracing lineage; comparing…

Checks blocking IO in async, unnecessary allocations, sync sleep, string concat in loops, redundant copies.

Runway common errors \u2014 AI video generation and creative AI platform.\n\

Runway deploy integration \u2014 AI video generation and creative AI\

Runway local dev loop \u2014 AI video generation and creative AI platform.\n\

Runway rate limits \u2014 AI video generation and creative AI platform.\n\

Runway sdk patterns \u2014 AI video generation and creative AI platform.\n\

When to activate: Rust tracing, logging, metrics, spans, instruments, OpenTelemetry, tracing-subscriber, prometheus, structured logging

Calculates and benchmarks critical SaaS growth metrics like ARR, MRR, churn, and LTV within the Claude Code environment.

Train sparse autoencoders to interpret model features.

Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas…

Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure…

Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality.