Analytics & Monitoring Agent Skills for Claude Desktop

Run comprehensive worker system benchmarks and performance analysis

Forecast workforce needs and plan talent supply strategies

Guides data source selection, customs microdata matching, and GVC decomposition for empirical manuscripts targeting The Journal of World…

Classify database writes by durability requirement (tracking vs critical) to eliminate false-positive data-loss alarms.

Rules for logs and error handling that shorten a root-cause hunt - log the decisions not the steps, wrap only the risky call, keep the…

Use when adding or reviewing log statements, or when deciding what level a message belongs at.

Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning.

Select and optimize embedding models for semantic search and RAG applications.

Combine vector and keyword search for improved retrieval.

Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking.

Use when the user asks to filter, query, search, or extract specific rows or columns from an Excel spreadsheet.

Integrates Yandex Metrika reporting for traffic analysis, conversion tracking, and marketing attribution directly within Claude.

Passive income portfolio analysis — activate when user asks about dividend yields, Treasury rates, REIT income, monthly passive income…

Assemble a sourced proprietary-data corpus map — sort every candidate data source by one test (can a foundation model already reach it?)…

Stack-neutral logging rules. Treat logs as a contract structured records (not free text), fixed schema (timestamp, severity, event, trace…

Run hypothesis tests, analyze A/B experiment results, calculate sample sizes, and interpret statistical significance with effect sizes.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full…

Fast tokenizers optimized for research and production.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers.

Verify and debug Zoom REST API calls and webhook deliveries from the platform's own records, instead of from your application's logs.