ascend-migration-analysis

ascend-migration-analysis is a skill for Claude Code from ascend-ai-coding/awesome-ascend-skills. It costs 137 tokens per session (1,938 once invoked), scanned A, original, no licence file.

A feasibility analysis for moving a PyTorch project from CUDA/GPU hardware to Ascend NPU hardware. It scans the code for hardware-specific dependencies and reviews device code, attention mechanisms, custom operations, distributed communication, precision, third-party packages, and compilation.

In plain words
What is it for?
Use it to assess whether a PyTorch model can run on Ascend NPUs and to identify migration options and likely problem areas.
Why use it?
It shows which parts may need replacement or adaptation before migration begins. This helps estimate the work needed for Transformer or DiT models, including video, language, and multimodal models.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ascend-inference plugin — 7 skills shipped together

Good fit Use it to assess whether a PyTorch model can run on Ascend NPUs and to identify migration options and likely problem areas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis
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.

Any agent
npx skills add ascend-ai-coding/awesome-ascend-skills --skill ascend-migration-analysis
Clone the repo
git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills

Made for: Claude Code.

Or install ascend-inference, the plugin that ships this one along with the rest of its 7 skills.

Its marketplace also offers this one on its own, as the plugin ascend-migration-analysis/plugin install ascend-migration-analysis after adding the marketplace above.

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 ascend-migration-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis/github.svg)](https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis)
Your own site
<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis/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 ascend-migration-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ascend-migration-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,938 The whole file, excluding the scripts and references it only reads on demand.
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.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.01938
Opus 5 $0.00068 $0.00969
Sonnet 5 $0.00027 $0.00388
Haiku 4.5 $0.00014 $0.00194

Measured 7d ago against content hash 606450f2f8e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ascend-migration-analysis 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.

skills/inference/ascend-migration-analysis/SKILL.md · 179 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

7 files beside SKILL.md 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 · 179 lines · 137 tokens per session scan A 606450f2f8e9

Subscribe to this mod's changes

ascend-migration-analysis is a skill published in the GitHub repository ascend-ai-coding/awesome-ascend-skills (168 stars, last pushed yesterday), with no licence file. It adds 137 tokens to every session and 1,938 once invoked, about $0.0007 per session on Opus 5. 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 2026-09-05.

Related

Other skills, from other repositories

ascend-transformer-boost

An index of skills for developing with Huawei’s Ascend Transformer Boost (ATB) library. It groups eight skills covering CANN setup, ATB testing, operator replacement design, and migration to ACLNN for Ascend NPU development.

Ascend/agent-skills · 90 tokens

atb-aclnn-operator-migration

A workflow for migrating ATB operators to ACLNN on Huawei Ascend 910B and 950 devices. ATB and ACLNN are libraries for implementing computations on Ascend hardware.

Ascend/agent-skills · 64 tokens

ascend-docker

Create Docker containers for Huawei Ascend NPU development with proper device mappings and volume mounts. Use when setting up Ascend development environments in Docker, running CANN applications in containers, or creating isolated NPU development workspaces. Supports privileged mode (default), basic mode, and full…

Ascend/agent-skills · 76 tokens

huawei-cloud-ascend-command

Huawei Ascend NPU natural language management skill, supporting both local direct connection and SSH remote modes. Provides comprehensive npu-smi command capabilities including device queries, configuration management, firmware upgrade, vNPU virtualization, certificate management, and compute power testing (FLOPS).…

huaweicloud/huaweicloud-skills · 261 tokens

huawei-cloud-ascend-remote-connect

Provides temporary SSH remote connection for Huawei Cloud Ascend devices with dynamic host/port/user/password input (in-memory only), disk management, NPU monitoring, container management, security auditing and log analysis; sensitive operations require user confirmation before execution Use this skillthis skill to…

huaweicloud/huaweicloud-skills · 115 tokens

arm-mcp-mcp

Provides AI assistants with specialized tools for Arm architecture development, migration, optimization, and profiling. Includes knowledge base search, code migration analysis, container architecture inspection, Arm Performix workload profiling, and assembly performance analysis.

Friz-zy/ai-capability-registry · 48 tokens