Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

analyze-nsys-profile

Query a captured PithTrain Nsight Systems profile to measure compute/communication overlap, locate exposed comm by DualPipeV stage, and inspect per-rank stream behavior. Use when the user asks to "analyze an nsys profile", "check overlap quality", "find exposed comm", "which stage is the bottleneck", or any question that starts from an existing `.nsys-rep` file. Assumes the trace was already captured (see capture-nsys-profile); provides query primitives the agent composes for the specific question being asked.

267 repo starsObserved in 1 repos
Testing & Quality
GitHub

capture-nsys-profile

Capture a Nsight Systems (.nsys-rep) profile of a short PithTrain run for performance analysis. Use when the user asks to "capture an nsys profile", "profile training", or "grab an nsys trace", or wants to inspect kernel timelines / pipeline behavior / all-to-all overheads. Adaptive over pipeline-parallel (PP), expert-parallel (EP), context-parallel (CP), and sequence length; size the global batch so the pipeline reaches steady state without producing a multi-GB .nsys-rep. Run 5 warmup steps + 1 profiled step from a released checkpoint.

267 repo starsObserved in 1 repos
Testing & Quality
GitHub

estimate-memory

Estimate peak GPU memory for a DualPipeV training run. Use when the user asks to "estimate memory", "will this fit in memory", "how much GPU memory", "check if this OOMs", "memory for training X on Y GPUs", or mentions memory planning for a training configuration. Translates natural-language descriptions of hardware, model, and training setup into the exact CLI arguments for `python -m tools.memory_estimator`.

267 repo starsObserved in 1 repos
Testing & Quality
GitHub

issue-verifier

Independent read-only verification for nearly finished GitHub issue work in this repository. Use when the user asks for 验收, 独立验证, 对齐验证, 完成前复核, or when a medium/large issue needs a separate acceptance pass before closing.

267 repo starsObserved in 1 repos
Testing & Quality
GitHub

perf-profile

结构化的性能分析工作流。识别瓶颈、与性能预算对比测量，并生成带有优先级排序的优化建议。

267 repo starsObserved in 1 repos
Testing & Quality
GitHub

test-ocas-openclaw

Regression test the OpenClaw Codex App Server plugin against a live local OpenClaw instance in Telegram or Discord. Use when the user wants an end-to-end OCAS manual test pass, wants to verify binding, `/cas_resume` or `/cas_status` flags for model/fast/yolo, approvals, plan mode, review, compact, status-card controls, split default-vs-full-access permission behavior, stop-button interrupt handling, rename, or other slash-command behavior, or wants reproducible bug notes from a live chat integration run.

266 repo starsObserved in 2 repos
Testing & Quality
GitHub

gdb-debugging

Guide for debugging Nanvix guests using GDB remote debugging over the microvm machine type. Use this when asked about attaching GDB, setting breakpoints, or stepping through kernel code.

266 repo starsObserved in 1 repos
Testing & Quality
GitHub

completeness-auditor

Verify every skill that claims "completed" produced a substantive audit/review artifact on disk with ≥ 5 explicit pass items. Runs as part of the independent audit layer that does not trust any single skill's self-declaration of done.

265 repo starsObserved in 2 repos
Testing & Quality
GitHub

consistency-auditor

Audit cross-media consistency of numbers, file names, symbols, and parameters across tex/code/results/data/appendix. Runs as an independent audit layer that does not trust any single skill's self-declaration of "done".

265 repo starsObserved in 2 repos
Testing & Quality
GitHub

matlab-code-reviewer

Review, debug, and verify MATLAB or Beita Tianyuan compatible modeling code against the validated method plan and expected artifacts.

265 repo starsObserved in 2 repos
Testing & Quality
GitHub