Loading...
Loading...
Found 13 Skills
Orchestrate multiple specialized agents working in parallel to debug independent problems. Use when encountering 3+ unrelated bugs or test failures in isolated modules. Matches each problem to the right expert agent and launches them concurrently via the Agent tool with worktree isolation. Supports all available subagent types.
Interactive hypothesis-driven debugging with documented exploration, understanding evolution, and analysis-assisted correction.
Hypothesis-driven autonomous debugging with real command validation
Regression troubleshooting workflow for hook/router/memory/search failures with enforced evidence and fix validation
Evidence-based 4-phase root cause analysis: Reproduce, Isolate, Identify, Verify. Use when user reports a bug, tests are failing, code introduced regressions, or production issues need investigation. Use for "debug", "fix bug", "why is this failing", "root cause", or "tests broken". Do NOT use for feature requests, refactoring, or performance optimization without a specific bug symptom.
Use this skill to learn using mcp-openmsx tools to control and automate the openMSX emulator, or when interacting with the openMSX emulator for develop/test/debug workflows or interactions that require direct control or information retrieval. Covers all MCP tools. Do NOT use for general agent tasks or when no direct openMSX interaction is required.
Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.
Replay-first debug flow for SGLang serving problems. Use when a live or recent server shows health-check failures, latency or throughput regressions, queue growth, timeouts, distributed stalls, crash dumps, wrong outputs after deploys, or PD/EP/HiCache issues, and the job is to turn the problem into a replay plus the right next debug tool.
Debug Streamlit frontend and backend changes using make debug with hot-reload. Use when testing code changes, investigating bugs, checking UI behavior, or needing screenshots of the running app.
Hard-bug DIAGNOSIS + FIX: reproduce the failure, name the cause, write a regression test, apply the minimal fix. Use whenever the user reports a bug, failure, flaky test, perf regression, error, or visible misbehaviour whose cause is not yet known — even if they only paste a symptom, stack trace, or failing test output, or say "why is X broken", "it stopped working", "it got slower", "this looks wrong". Do NOT start debugging inline without this skill: if your next step would be forming hypotheses about an unexplained failure, invoke /pasteurize first. Do NOT use for review-only diffs (/age), feature design (/mold), fixes where the cause is already known (/cook), or when the user opted out of writes (/culture).
Structured debug mode focused on root-cause confirmation and controlled fixes.
Used when performing GDB debugging on target boards via PlatformIO's built-in debugging features, supporting download-and-halt, attach-only, and crash context analysis.