“Debugging”

Debug broken runtime/environments by checking logs and observability first, then code.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

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

How to use ragcode tools for fast root-cause analysis and debugging

Debug and fix failing tests or errors

Debug issues through structured investigation, failing test creation, and targeted fixes.

Techniques and tools for testing and debugging MCP servers.

4-phase root cause debugging: understand bugs before fixing.

Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb.

Debug a failure methodically.

引导系统化的 root cause debug。当测试失败、构建中断、行为与预期不符，或遇到任何意外错误时使用。当你需要用系统化的方法定位并修复 root cause、而不是靠猜时使用。

把「只在本機／測試環境才要有」的 debug 改動（例如印出 req/res body）套進當前 repo，並單獨包成一個 temp commit，測完可以整包丟掉。也負責維護這份 debug 改動清單：使用者說「再加一個測試用改動」「記下這個 debug patch」時，把新的一筆寫進 catalog。觸發：套…

Sysinternals DebugView CLI (DbgViewCli) for capturing and analyzing usermode and kernel-mode Windows debug output from the command line.

You are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools.

Structured debugging workflow that teaches the debugging process, not just fixes the bug.

Debug helper - Systematic bug investigation and root cause analysis.

Use for debugging DSPy programs, inspect_history, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.

Four-phase root cause investigation for bugs and unexpected behavior

Four-phase root cause investigation process for diagnosing bugs, errors, and unexpected behavior

Structured debugging when systematic-debugging is not installed.

Explicit debugging instruction for developers: five-stage framework, hypothesis testing, tools, and common error patterns.

Debug errors and exceptions.

Use after an agent-qa run has failed and you need to debug, patch, and verify the issue using MCP evidence, logs, artifacts, and local code changes instead of…

Systematic debugging.