Analytics & Monitoring Agent Skills for Claude Code

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing.

Audit, plan, add, improve, or review production logging and observability for a selected class, package, migrated operation, module…

Guide for adding new report cards to ClaudeBar that analyze local data sources and display metrics with comparison deltas.

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform.

Guide for debugging with targeted log injection and runtime analysis

Guides agent architecture decisions through consultative analysis.

Claude Agent SDK build harness with a Planner/Builder/Evaluator loop.

Builds self-verifying experiment laboratories and measurement feedback loops for optimization, debugging, visual fidelity, quality, cost…

End-to-end Agent Observability pipeline for an instrumented ml_app — classify production traces, root-cause failures, bootstrap…

Root cause analysis on production LLM traces.

Read-only observation of an agent's parent, siblings, and direct children.

Use when synthesizing perf findings into evidence-backed recommendations and decisions.

Use when managing perf baselines, consolidating results, or comparing versions.

Use when running performance benchmarks, establishing baselines, or validating regressions with sequential runs.

Use when mapping code paths, entrypoints, and likely hot files before profiling.

Use when appending structured perf investigation notes and evidence.

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

Finds and recalls past AI agent sessions across Cursor, Codex, Claude Code, and other hosts using activity keywords, projects, or session…

Agent 会话可视化 / session timeline: execution maps for Cursor, Codex, Claude Code, Workbuddy, kimi-code threads (ID or name)…

Make NVIDIA OO agent types render beautiful documentation for the LLM — doc(), spec(), hidden, Annotated field descriptions, and…

Patterns and techniques for evaluating and improving AI agent outputs.