← All skills

torch-npu-comm-test

80 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By ascend-ai-coding/awesome-ascend-skills (GitHub) · coding · 184 stars · scanned at commit 75ec89c

通过 PyTorch torch.distributed 接口测试昇腾 NPU 通信算子性能。支持指定任意 tensor shape、dtype，使用 torchrun 启动，贴近真实训练场景的通信算子测试与性能分析。Use for testing collective communication operators (AllReduce, AllGather, ReduceScatter, etc.) with specific tensor shapes via torch.distributed on Ascend NPU.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'torch-npu-comm-test' ] || [ -L ~/.agents/skills/'torch-npu-comm-test' ]; then echo 'A skill folder named torch-npu-comm-test already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ascend-ai-coding/awesome-ascend-skills' "$d" && git -C "$d" checkout --quiet '75ec89ce9d401be8ac95980e1c3f42f8d4315057' -- 'skills/training/torch-npu-comm-test' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/training/torch-npu-comm-test' ~/.agents/skills/'torch-npu-comm-test' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'torch-npu-comm-test' ~/.claude/skills/'torch-npu-comm-test' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for ascend-ai-coding/awesome-ascend-skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/ascend-ai-coding/awesome-ascend-skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/ascend-ai-coding/awesome-ascend-skills/)

Score history