external-cannbot-torch-npugraph-ex-skills

external-cannbot-torch-npugraph-ex-skills is a plugin for Claude Code from ascend-ai-coding/awesome-ascend-skills. Its manifest loads nothing; the 6 skills it bundles cost 843 tokens per session together, scanned A, original, no licence file.

A set of six skills for using PyTorch graph features on Huawei Ascend NPUs, including code templates and error diagnosis.

In plain words
What is it for?
It helps with graph-mode development, compilation errors, runtime errors, troubleshooting, and putting custom operators into the NPU graph.
Why use it?
It helps developers investigate graph-compilation and runtime problems when moving PyTorch workloads onto Ascend hardware.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit It helps with graph-mode development, compilation errors, runtime errors, troubleshooting, and putting custom operators into the NPU graph.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add ascend-ai-coding/awesome-ascend-skills/plugin install external-cannbot-torch-npugraph-ex-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for external-cannbot-torch-npugraph-ex-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills/github.svg)](https://agentmods.dev/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills)
Your own site
<a href="https://agentmods.dev/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills"><img src="https://agentmods.dev/badge/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for external-cannbot-torch-npugraph-ex-skills

Your own site · 80×15
<a href="https://agentmods.dev/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills"><img src="https://agentmods.dev/badge/plugins/ascend-ai-coding/awesome-ascend-skills/external-cannbot-torch-npugraph-ex-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 6 skills cost 843 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Security

Grade A, and why

external-cannbot-torch-npugraph-ex-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#external-cannbot-torch-npugraph-ex-skills · 24 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

1 file beside marketplace.json#external-cannbot-torch-npugraph-ex-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 24 lines scan A 2220a87a1624

Subscribe to this mod's changes

external-cannbot-torch-npugraph-ex-skills is a plugin published in the GitHub repository ascend-ai-coding/awesome-ascend-skills (167 stars, last pushed yesterday), with no licence file. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other plugins, from other repositories

embedded-debugger

Embedded debugger workflow for probe-rs targets. Provides a CLI-first skill and optional MCP server for probe discovery, target checks, flashing, memory access, and RTT workflows.

Adancurusul/embedded-debugger-mcp · not measured

personal-os

Personal macOS workstation operations toolkit: structured root cause analysis and diagnostics for your own Macs.

basher83/lunar-claude · not measured

wireless-multiplex-state-audit

Cross-driver audit methodology for protocol-multiplex state machines in wireless drivers (Wi-Fi 7 EMLSR/MLSR, Wi-Fi Direct, NAN, TDLS, FTM, AWDL-class). Identifies the multiplex primitive each vendor uses to time-share one radio across multiple links/protocols, enumerates state-transition surfaces, and hunts the…

dmaynor/dmaynor-skills-marketplace · not measured

unifi

Manage UniFi network devices, clients, sites, and diagnostics via the unifi CLI (github.com/ThrownLemon/unifi-cli). Provides commands for client/device/site management, a network-awareness skill, and a troubleshooter agent.

ThrownLemon/claude-code-plugins · not measured

unraid-troubleshooter

Diagnose and fix Unraid (Lime Tech NAS OS) issues — array start/stop, parity, disabled disks, Docker macvlan/ipvlan, VM/GPU passthrough, BTRFS/ZFS pools, shares, plugins, Community Apps, boot/license, with version-aware release notes lookup.

GoogilyBoogily/googilyboogily-claude-power-tools · not measured

linux-troubleshooter

Diagnose and fix Linux desktop issues — Nvidia/Mesa GPU drivers, Wayland/X11 display, PipeWire audio, systemd, boot, suspend, networking, sandbox apps.

GoogilyBoogily/googilyboogily-claude-power-tools · not measured