observability
Telemetry, metrics, tracing, and observability for Elixir/BEAM applications
আপনার এজেন্টের জন্য উপযুক্ত সক্ষমতা খুঁজে নিন।
Telemetry, metrics, tracing, and observability for Elixir/BEAM applications
Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.
Systematic RL debugging - diagnose learning failures, common bugs, diagnosis trees
Control Chrome browser through MCP for testing, debugging, network analysis, and performance profiling. Use when testing web apps, measuring Core Web Vitals, analyzing network requests, debugging console errors, or when the user mentions Chrome DevTools, performance traces, or browser automation.
Analyse throughput, case duration, and activity sojourn times from the filtered log.
Analyze script failures to identify source components and propose fixes
Performance optimization strategies. Use ONLY after profiling identifies bottlenecks.
C++ debugging for segfaults, memory corruption, threading issues, and linker/ABI problems. Use when encountering crashes (exit code 139/SIGSEGV), memory leaks, data races, undefined behavior, or when debugging native Node.js addons, FFmpeg integrations, or any C++ code that crashes mysteriously.
Reverse-engineer specifications from undocumented code. Use for legacy systems or creating documentation from implementations.
Review local codebase for bugs and CLAUDE.md compliance using multi-agent analysis
Time-based sampling profiler showing WHERE execution time is spent (wall-clock time, not frequency). Provides histogram with self/total time, compilation tiers (T0/T1/T2), and flame graphs. Use as FIRST step to identify hot functions consuming most time. Low overhead, suitable for longer runs. Pair with tracing-execution-counts to understand time-per-execution vs execution frequency.
Production hardening review for the OpenEvent backend. Use when scanning for LLM smells, noisy prints, swallowed exceptions, dev-only defaults, fallback diagnostic leakage, and inconsistent error/logging patterns; produce a prioritized, PR-sized cleanup plan.
Use when encountering any bug, test failure, or unexpected behavior in C#/.NET code before proposing fixes; applies to gRPC services, EF Core queries, async operations, and build failures
iOS Simulator interrogation: simctl screenshots/video, Web Inspector for web content, Instruments for native behaviors.
NetGraph contributor development workflow. Use when: setting up dev environment, running tests or lint, fixing CI failures, running performance benchmarks, troubleshooting venv issues, or asking about make targets. For running scenarios and interpreting results, use netgraph-dsl instead.
Four-phase structured debugging methodology. Use when (1) tests fail unexpectedly, (2) functions produce wrong values, (3) systems show anomalous results, (4) unexpected errors appear, (5) performance regresses, (6) multiple quick fixes have already failed. Enforces root cause investigation before any fix attempt.