ai-for-science-ai4s-basic

ai-for-science-ai4s-basic is a skill for Claude Code from ascend-ai-coding/awesome-ascend-skills. It costs 96 tokens per session (5,681 once invoked), scanned A, original, no licence file.

An AI-for-science migration guide for moving CUDA-based projects from NVIDIA hardware to Huawei Ascend NPUs. It covers projects using PyTorch, TensorFlow, or vLLM, including code changes and distributed setups.

In plain words
What is it for?
Inspecting code, adapting operations, replacing unsupported third-party libraries, changing distributed training, and checking migrated projects.
Why use it?
It helps identify and fix the hardware-specific parts that prevent a CUDA project from running on Ascend. It also provides a structured path for checking the environment, replacing libraries, and validating the result.

Skill for Claude Code

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

Part of the ascend-ai-for-science plugin — 14 skills shipped together , and of ai-for-science

Good fit Inspecting code, adapting operations, replacing unsupported third-party libraries, changing distributed training, and checking migrated projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic
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 ai4s-basic
Clone the repo
git clone --depth 1 https://github.com/ascend-ai-coding/awesome-ascend-skills

Made for: Claude Code.

Or install ascend-ai-for-science, the plugin that ships this one along with the rest of its 14 skills.

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 ai-for-science-ai4s-basic

README.md
[![agentmods](https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic/github.svg)](https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic)
Your own site
<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic/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 ai-for-science-ai4s-basic

Your own site · 80×15
<a href="https://agentmods.dev/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic"><img src="https://agentmods.dev/badge/skills/ascend-ai-coding/awesome-ascend-skills/ai4s-basic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,681 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 $0.00096 $0.05681
Opus 5 $0.00048 $0.02840
Sonnet 5 $0.00019 $0.01136
Haiku 4.5 $0.00010 $0.00568

Measured 7d ago against content hash 455aab679b93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-for-science-ai4s-basic 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_npu_basics.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ai-for-science/models/ai4s-basic/SKILL.md · 559 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

4 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 · 559 lines · 96 tokens per session scan A 455aab679b93

Subscribe to this mod's changes

ai-for-science-ai4s-basic 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 96 tokens to every session and 5,681 once invoked, about $0.0005 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

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

davila7/claude-code-templates · 63 tokens

ray-data

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

davila7/claude-code-templates · 70 tokens

mlflow

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.

davila7/claude-code-templates · 33 tokens

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform.

davila7/claude-code-templates · 39 tokens

ray-train

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

OpenLAIR/dr-claw · 63 tokens