Loading...
Loading...
Found 205 Skills
Use when diagnosing unexpected behavior, failed workflows, bugs, browser or Node.js runtime issues, logs, traces, or when preparing a root-cause hypothesis. 诊断异常、定位 bug、判断修复方向时使用：先建立证据表，区分运行时事实和代码推断，避免多层猜测；证据不足时添加 copy-friendly 浏览器日志或本地 Node.js JSONL 日志。
Full debugging workflow — reproduce the bug with a failing test, perform root cause analysis, then implement a minimal fix.
Compares two `tuist cache` runs to identify cache hit rate changes and root-cause analysis of cache invalidation. Can be invoked with cache run IDs, dashboard URLs, or branch names.
Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
Analyze arguments, detect biases, evaluate claims, and improve reasoning. Use when asked to fact-check, identify logical fallacies, evaluate arguments, analyze predictions, find root causes, or think adversarially about plans. Triggers include "evaluate this argument", "logical fallacies", "fact check", "analyze the claims", "identify biases", "devil's advocate", "red team this", "root cause".
Structured debug mode focused on root-cause confirmation and controlled fixes.
Systematic debugging workflow — reproduce, investigate, hypothesize, fix, and prevent. Covers root cause analysis, bug category strategies, evidence-based diagnosis, and post-mortem documentation.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Fix a known bug in the Rock RMS codebase. Guides Claude through root cause analysis, minimal correct fix, and a release-note commit message. Use when the user says "fix this bug", "bugfix", "this is broken", "debug this", describes a bug with file paths or issue numbers, or pastes an error/stack trace with intent to fix. Also use when a bug is found by another skill (e.g. /review-conversion, /check) and the user wants it fixed. Do NOT use for: finding bugs (use /check or /review-conversion), adding features, or refactoring.
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Write a structured incident postmortem or post-incident review. Use when asked to write a postmortem, incident report, P1/P2 review, outage report, or RCA (root cause analysis). Generates a blameless postmortem with timeline, root cause, contributing factors, impact summary, and action items.