Analytics & Monitoring Agent Skills

Log Summary Date Ranges

16

Aggregates log file entries across specific date ranges to produce detailed severity statistics and structured CSV reports.

Environmentalist Analyst

16

Analyzes projects and systems through the lens of environmental science, ecology, and long-term sustainability frameworks.

FDA Database Explorer

16

Accesses and analyzes comprehensive FDA regulatory data for drugs, medical devices, and food safety through the openFDA API.

Performance Engineering

16

Optimizes software performance through systematic profiling, benchmarking, and evidence-based engineering workflows.

Root Cause Analysis

16

Systematically diagnoses software failures and system incidents to identify and resolve the underlying source of errors.

Regex Log Parsing

16

Constructs complex regular expressions to extract and validate structured data from log files using a systematic decomposition strategy.

Session Replay & Trace Analytics

16

Analyzes Claude Code session traces to optimize token consumption and diagnose technical performance issues.

Context Management

16

Optimizes Claude's context window through proactive token monitoring, intelligent snapshots, and selective rehydration.

Retrospective Validation

15

Validates methodology effectiveness using historical session data to predict performance without the risks of live deployment.

Go Code Refactoring & Optimization

15

Refactors complex Go codebases using automated metrics and BAIME-aligned protocols to reduce cyclomatic complexity and improve test coverage.

Technical Debt Management

15

Transforms subjective code debt into objective, data-driven paydown strategies using the industry-standard SQALE methodology.

Observability Instrumentation

15

Implements the three pillars of observability—structured logging, metrics, and distributed tracing—to provide deep visibility into application health and performance.

Error Recovery & Diagnosis

15

Automates the detection, classification, and resolution of system errors using a 13-category taxonomy and systematic recovery patterns.

SRE Incident Response

15

Manages production incidents using SRE methodologies for rapid investigation, mitigation, and postmortem documentation.

Grey Haven Observability & Monitoring

15

Implements production-grade observability for Cloudflare Workers using structured logging, real-time log streaming, and custom performance metrics.

Performance Optimization

15

Analyzes and optimizes application performance across algorithms, databases, and frontend frameworks to resolve bottlenecks and reduce latency.

Observability Engineering

15

Implements production-grade monitoring, logging, and tracing systems to ensure application reliability and performance.

Smart Debugging

15

Diagnoses complex software errors using automated stack trace analysis and systematic root cause investigation.

Technical Debt Management

15

Quantifies and manages technical debt using the SQALE methodology to prioritize refactoring and establish objective code quality benchmarks.

Observability Instrumentation

15

Implements comprehensive logging, metrics, and distributed tracing to ensure production reliability and performance monitoring.

Error Recovery & Workflow Optimization

15

Implements a systematic error-handling methodology using a 13-category taxonomy to diagnose, recover from, and prevent session failures.

Memory Profiling & Leak Detection

15

Identifies memory leaks and optimizes allocation patterns in JavaScript, TypeScript, and Python applications to prevent performance degradation.

Agent Prompt Evolution

15

Systematically tracks and optimizes the specialization of AI agents within workflows to improve performance and reusability.

Prometheus Go Code Review

14

Validates Prometheus metrics implementation in Go applications to ensure optimal observability and performance.

Google Tag Manager Expert

14

Simplifies GTM implementations by providing expert guidance on tags, triggers, variables, and data layer configurations.

Memtrace Allocation Profiler

13

Profiles and optimizes OCaml memory allocations to eliminate boxing overhead and improve application performance.

Distributed Tracing & Observability

13

Implements comprehensive request tracking across microservices using Jaeger and Tempo to identify performance bottlenecks and service dependencies.

Prometheus Configuration

13

Configures Prometheus for comprehensive metric collection, alerting, and observability across infrastructure and applications.

SLO Implementation Framework

13

Implements service reliability targets using SLIs, SLOs, and error budgets to balance innovation velocity with system stability.

Kafka Observability Expert

13

Implements comprehensive Kafka monitoring using Prometheus and Grafana to track cluster health, consumer lag, and broker performance.