“Debugging”

系统化排查 bug：复现、定位根因、最小修复

에러 진단+수정.

Triage stack traces and failures — reproduce, locate root cause, propose a minimal fix.

按修复方案改代码，跑相关测试全绿才算修好

Diagnose failed Quark installation, PTQ execution, script generation, or export attempts.

AI-Meeting 排障剧本 Skill。用于处理面试卡住、运行时超时、重复请求、恢复失败、媒体链路异常和跨层问题定位；当问题现象比改动目标更清晰，或者需要先定位层次再决定怎么修时使用。

Find the cause of failing behavior and fix it when requested.

Debug and test tmux pane status detection for AI agents (opencode, claude, amp).

Start from a failure, not a filename — turn a stacktrace, failing test, or diff into the exact code that matters, then read it.

面向软件故障的证据驱动自主调试。用于调查 bug、回归、崩溃、错误结果、性能问题，或生成并验证最小修复。工作区存在 .zoo/debug/ Case、被唤醒继续调查，或需要经 zdebug 记录调查时加载。

Use when a workflow run failed, hung, or produced no artifacts — an ordered triage from run id to root cause across status, stage logs, S3 evidence, pod-level…

Use when encountering any bug, test failure, unexpected behavior, or error message — before proposing any fix

Trace customer, catalog, order, event, webhook, and recommendation failures across Shopify, Klaviyo, and a Django backend.

Use when the answer likely lives OUTSIDE this repo: debugging an error from a library/framework/API, checking whether an SDK signature is current, evaluating…

Diagnose PHP bugs systematically — reproduce, isolate, hypothesize, verify.

使用捕获、诊断、受控恢复和内省报告的结构化自我调试工作流程，用于 AI 智能体失败。

使用捕获、诊断、受控恢复和内省报告的 AI Agent 失败结构化自我调试工作流。

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

Capture a complete debugging snapshot of a web page using Argus — console logs, network traffic, and a screenshot.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern…

Diagnoses .NET Framework CLR activation issues using CLR activation logs (CLRLoad logs) produced by mscoree.dll.

Diagnose and fix a reproducible defect through root-cause evidence.

Alias: now /lv-test (manual walkthrough) and /lv-bug.

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