atc-model-converter

atc-model-converter is a skill for Claude Code, Codex from Ascend/agent-skills. It costs 142 tokens per session (7,098 once invoked), scanned A, original, MulanPSL-2.0.

A toolkit for converting machine-learning models to run on Huawei Ascend NPU hardware. It covers exporting PyTorch models to ONNX, converting ONNX files to Ascend .om files, and adapting the complete inference setup.

In plain words
What is it for?
Use it to discover model input details, export PyTorch models, create .om models with ATC, and adapt model inference for Ascend devices.
Why use it?
It organizes the conversion steps and handles model inputs, parameters, and different CANN software versions in one workflow.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

Good fit Use it to discover model input details, export PyTorch models, create .om models with ATC, and adapt model inference for Ascend devices.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ascend/agent-skills/atc-model-converter
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/agent-skills --skill atc-model-converter
Clone the repo
git clone --depth 1 https://github.com/Ascend/agent-skills

Made for: Claude Code, Codex.

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 atc-model-converter

README.md
[![agentmods](https://agentmods.dev/badge/skills/ascend/agent-skills/atc-model-converter/github.svg)](https://agentmods.dev/skills/ascend/agent-skills/atc-model-converter)
Your own site
<a href="https://agentmods.dev/skills/ascend/agent-skills/atc-model-converter"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/atc-model-converter/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 atc-model-converter

Your own site · 80×15
<a href="https://agentmods.dev/skills/ascend/agent-skills/atc-model-converter"><img src="https://agentmods.dev/badge/skills/ascend/agent-skills/atc-model-converter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,098 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 $0.00142 $0.07098
Opus 5 $0.00071 $0.03549
Sonnet 5 $0.00028 $0.01420
Haiku 4.5 $0.00014 $0.00710

Measured 10d ago against content hash 0a1aeef4b6ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

atc-model-converter 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 10d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/check_env_enhanced.sh, scripts/compare_precision.py, scripts/export_onnx.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/atc-model-converter/SKILL.md · 679 lines

The source is not reproduced here

Licensed MulanPSL-2.0

The repository is licensed MulanPSL-2.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 10d ago First seen · 679 lines · 142 tokens per session scan A 0a1aeef4b6ff

Subscribe to this mod's changes

atc-model-converter is a skill published in the GitHub repository Ascend/agent-skills (40 stars, last pushed 4mo ago), licensed MulanPSL-2.0. It adds 142 tokens to every session and 7,098 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 2026-08-30.

Related

Other skills, from other repositories

submit-github-bug-issue

Use when converting QA findings, black-box failures, red-team reports, regression evidence, or local bug notes into GitHub Issues for NVIDIA/TensorRT-Model-Connect. Standardizes checking issue templates, checking labels, de-duplicating existing issues, drafting a bug report, creating the issue on GitHub, applying the…

NVIDIA/TensorRT-Model-Connect · 82 tokens

submit-github-pr

Use when publishing an existing TensorRT-Model-Connect change as a GitHub pull request. Verifies authenticated repository access, branch and diff scope, validation evidence, commit identity, reviewer-facing text, exact pushed head, and the created draft PR without merging it.

NVIDIA/TensorRT-Model-Connect · 58 tokens

optimize-model-precision

Evaluate supported precision, quantization, or selected FP32-layer choices for one TensorRT-Model-Connect family with matched correctness and timing.

NVIDIA/TensorRT-Model-Connect · 34 tokens

transform-model

Add a Hugging Face or local checkpoint to TensorRT-Model-Connect as a self-contained family, or extend the family that already owns it.

NVIDIA/TensorRT-Model-Connect · 33 tokens

debug-trt-mismatch

Diagnose a TensorRT-Model-Connect family whose native output disagrees with its declared reference or family-owned correctness contract.

NVIDIA/TensorRT-Model-Connect · 31 tokens

profile-model

Measure one TensorRT-Model-Connect model through its public Task API or run a checked-in performance-matrix entry with comparable evidence.

NVIDIA/TensorRT-Model-Connect · 30 tokens