“Debugging”

Troubleshoot ChainGPT API errors and issues.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Windows环境下Claude Code插件Hook执行错误的诊断与修复。当遇到hook error、cannot execute binary file、.sh regex误匹配、WSL/Git Bash冲突时使用。

Diagnose HorizontalPodAutoscaler failures (not scaling, metrics unavailable, target mismatch).

Diagnose Ingress failures (rules not matching, backend unreachable, TLS errors, no address assigned).

Diagnose Job and CronJob failures (BackoffLimitExceeded, DeadlineExceeded, pods failing, CronJob not triggering).

Guides systematic root-cause debugging with the Stop-the-Line rule and a reproduce → localize → reduce → fix → guard → verify triage checklist.

Debug and fix bugs with a regression-test Red-Green cycle and a living Debug Note.

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

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

Systematic debugging with the cognitive OS.

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 /…

Systematically debug issues in code.

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

Run and debug Salesforce Apex tests using agent-friendly CLI output.

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

Guide systematic debugging through hypothesis generation, evidence collection, and verification.

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

Apply this skill whenever the user asks to debug, review, audit, or find problems in code — regardless of language or framework.

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.

Systematic root-cause debugging when something is broken — a failing test, a broken build, a runtime error, a flaky or non-reproducible bug, or behaviour that…