Analytics & Monitoring Agent Skills for Claude Code

This skill enables Claude to detect and resolve performance bottlenecks in applications.

DevGlobe activity tracker - appear on the interactive developer globe while coding with Codex.

Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown.

Use when a Windows process has high or growing memory usage — 内存占用高、RAM 持续增长、memory leak、OOM、private bytes/RSS 异常，或被问"到底哪一层占用最大".

Use when the user wants to run a diffusers pipeline from a terminal (one-off generation, batch jobs, smoke-testing a new model), run on HF…

Use to finalize Science display items — panel/word budget, column-width sizing, minimum font sizes, color-accessibility, and showing the…

Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.

Execute this skill automates the setup of distributed tracing for microservices.

System diagnostics and health checks for Diverga plugin.

Implement monitoring, logging, and tracing for Documenso integrations.

Documentation usage analytics and insights.

Avoid applying domain knowledge constraints that hurt ML model performance.

Provide reusable recipes for common continuous corpus runs.

Debugs Windows and Linux/macOS applications (native, .NET/CLR, mixed-mode) with WinDbg MCP (crash dumps, !analyze, !syncblk, !dlk…

Route Doubleword LLM inference and data-processing jobs across realtime, async, and batch tiers using the dw CLI or OpenAI-compatible API.

Establish baseline → snapshot → compare → history monitoring for any KPI, config, or metric that can drift during PRD v0.8 Deployment & Ops.

Render token and wall-time rollups from `.agentic/events.jsonl`.

Translates natural language computer vision requirements into structured video recognition algorithm configurations for AI vision platforms.

Use when the user asks to filter, query, search, or extract specific rows or columns from a tabular data file (CSV, TSV, Parquet, Arrow…

Benchmark planner×implementer LLM pairings on a real GitHub issue and chart quality-per-dollar.

Continuous supplier and supply chain risk monitoring with automated alerts