“Debugging”

Use when encountering a bug, failing test, broken integration, or unexpected behavior, before proposing fixes.

Guides systematic root-cause debugging.

Debug GPU kernel crashes in SGLang (CUDA and ROCm) using @debug_kernel_api logging — illegal memory access, device assert, NaN/Inf, wrong shapes.

Diagnose WHY a failing verification won't converge — reproduce first, hypothesis + discriminating experiment, classify the defect (code / test / plan /…

Embedded debug MCP: serial, flash verify, fault decode, 45-pattern log analyzer, driver library

Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues.

Use when a bug, failing test, incident, or unexpected behavior has unknown cause and scope is not yet frozen.

Use when a bug, failing test, crash, performance regression, build failure, or unexplained behavior needs diagnosis.

Use to investigate unknown failures, business incident reports, or incomplete diagnoses after align, within active tasks, or on diagnosis-only requests; not…

Use when a DPF symptom needs a root cause — a failing build, a wedged runtime, a stuck job, wrong output.

Investigate a bug or unexpected result before changing code.

定位原因不明、跨模块或反复出现的程序故障、测试失败与异步状态异常，沿数据流取证并用最小实验验证根因。用于排错，不用于普通功能规划、纯文案修改或无故障的例行审查。

在编译、导入、测试或运行失败时使用，要求依据错误输出定位根因并实施最小修复；不在没有失败证据时触发大范围重写。

Game debugging and root cause analysis.

A skill with debug mode enabled

Use when debugging issues.

Debug or verify a local UI end to end in the user's existing Chrome tab, with temporary runtime probes and a manual browser fallback.

Runs a structured production-incident investigation that forces evidence-first hypothesis ranking before any code change.

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

Hypothesis-driven debugging skill.

A flexible workflow for diagnosing crashes, incorrect behavior, regressions, intermittent failures, and unclear error reports before changing code.

Diagnose a failing or misbehaving sync — fetch run logs, identify errors, cross-reference with code, and suggest fixes

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

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools.