“debugging”

Debug Astroclaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before…

Create a debugging reset handoff for a fresh agent, preserving the issue, reproduction, impacted files, commands run, attempted fixes, failures, findings, and…

Debug AOTInductor (AOTI) errors and crashes.

Disciplined diagnosis loop for hard bugs and performance regressions.

Use the moment any test fails twice, when a build breaks unexpectedly, when the code-reviewer rejects code, when the implementer reports BLOCKED, when the…

Structured debugging with mandatory evidence gathering before any fix attempt.

Expert debugging methodology.

Create debugging tools for AI behavior visualization and analysis

Systematically find root causes and fix bugs.

Debug experiment code with structured error analysis.

Root-cause route for actual bugs, failing tests, build errors, crashes, stack traces, and unexpected behavior.

Android diagnosis workflow for crashes, ANRs, incorrect UI state, coroutine or Flow bugs, data loading failures, and Compose rendering issues.

Run the st-debug agent on demand for one task of the current feature, then verify with st-verify.sh (test green, no added comment lines).

Analyze errors and debug output to find root causes

Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends

Chrome DevTools MCP ile browser debugging.

Systematic debugging: reproduce, isolate, form hypotheses, instrument, fix, and add regression tests.

Debugs failures using reproduce-isolate-fix-verify steps instead of random changes.

Systematic debugging expertise - 4-phase root cause process, evidence gathering, and hypothesis testing.

Launch ephemeral debug container in running pod for interactive debugging.

Use when the user asks to debug, diagnose, reproduce, or fix a hard bug, flaky failure, crash, incorrect result, or performance regression.

Use when diagnosing a bug, failing check, unexpected behavior, or production incident before changing code.

Systematically debug issues with persistent state across context resets.

This skill should be used when debugging frontend/UI bugs that need runtime evidence.