Set up and use Gonzo, the open-source terminal log analysis tool. Detects deployment platforms (Vercel, Supabase, K8s, Docker, AWS, Cloudflare, Fly, Render, Railway, Netlify), generates the right pipe command with platform-specific normalizers, and configures AI analysis. Use when the user wants to tail, watch, stream, or analyze logs in their terminal.
After fixing a bug, finds and rates other instances of the same anti-pattern. Self-validates the constructed pattern against the pre-fix file before scanning. Each match is classified individually as BUG / WATCH / OK / REVIEW.
Set up and use Dstl8 for AI-native observability. Triggers on: install or configure Dstl8 (CLI, sources, MCP); incident triage; root cause analysis; deployment verification; cross-environment correlation; pre-coding production context. Installing this plugin auto-registers the Dstl8 MCP server in Claude Code (the CLI must be installed and authenticated separately — the skill walks through it).
Trace Java, Python, Node, TypeScript and Go execution without modifying source, then analyze the resulting trace. Ships the flowtrace CLI on PATH and a flowtrace://runtimes capability resource.
Triage and fix Mushi bug reports without leaving Claude Code: hosted MCP (OAuth sign-in, no keys) + a mushi-debugger subagent that pulls reports, diagnosis, and fix context
Use when the user asks to run Root Cause Analysis (RCA), debug a production incident, analyze an error log or stack trace, or trigger Steadwing. Self-registers a Steadwing agent, triggers RCA via the Steadwing API, and can install a hook that detects production-style errors and offers RCA.
Superpowers integration for MemoryLens memory profiling. Enhances systematic-debugging with .NET memory snapshot analysis, leak detection, and before/after fix validation when MemoryLens MCP tools are available.
Trace Python runtime call flow, arguments, return values, errors, and timing via a decorator, then read the generated trace to debug what actually happened.
Guides you through diagnosing and fixing a bug yourself instead of patching it for you. Gathers the evidence, poses ranked hypotheses, and walks the investigation one step at a time while you form the diagnosis and write the fix.
Debug a Cortex-M target (STM32, EFM32, nRF, any SWD/JTAG MCU) live over OpenOCD or SEGGER JLinkGDBServer — locally or through a reverse SSH tunnel — with an evidence-first, probe-agnostic methodology.
Set up and use Gonzo, the open-source terminal log analysis tool. Detects deployment platforms (Vercel, Supabase, K8s, Docker, AWS, Cloudflare, Fly, Render, Railway, Netlify), generates the right pipe command with platform-specific normalizers, and configures AI analysis. Use when the user wants to tail, watch, stream, or analyze logs in their terminal.
Drive and debug Chrome from Claude: DOM and network inspection, performance traces, LCP and memory-leak analysis, accessibility auditing. Bundles the official chrome-devtools-mcp server plus its six skills.