Core AI Models is a toolkit for exporting AI models, creating model components in Python, and running exported models in macOS and iOS apps through Swift utilities. It is for developers building on-device AI applications with Core AI. Its catalogue skills and plugin help coding agents work with the model export and runtime tooling.
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.
git clone --depth 1 https://github.com/apple/coreai-modelsWrote 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.
[](https://agentmods.dev/plugins/apple/coreai-models/skills)<a href="https://agentmods.dev/plugins/apple/coreai-models/skills"><img src="https://agentmods.dev/badge/plugins/apple/coreai-models/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.
<a href="https://agentmods.dev/plugins/apple/coreai-models/skills"><img src="https://agentmods.dev/badge/plugins/apple/coreai-models/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
coreai-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 1mo 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.
What it actually says
{
"name": "coreai-skills",
"description": "Skills for authoring, exporting, compiling, and running PyTorch models on Apple silicon via Core AI.",
"version": "0.1.0",
"author": {
"name": "Apple"
},
"keywords": [
"coreai",
"on-device-ai"
]
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 300 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 13 lines scan A 54943190a5e5
coreai-skills is a plugin published in the GitHub repository apple/coreai-models (2,194 stars, last pushed yesterday), licensed BSD-3-Clause. 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 2026-08-30.
Other plugins, from other repositories
dgx-spark-ops
NVIDIA DGX Spark (GB10 Grace Blackwell) environment operations: aarch64/CUDA-13 stack setup, training gotcha preflights, and unified-memory/thermal management for local ML workloads.
nvidia-skills
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.
amd-skills
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom, and analyze GPU kernel and PyTorch trace performance.
intel-gpu-ai-skills
Agent Skills for running, benchmarking, profiling, and fixing arbitrary Hugging Face safetensors models on Intel GPUs. Container-first, upstream-only, Battlemage / Arc / Arc Pro / Data Center GPU Max.
awesome-ascend-skills marketplace
A comprehensive knowledge base for Huawei Ascend NPU development, structured as distributed AI Agent Skills. Includes npu-smi device management, HCCL performance testing, and ATC model conversion.
ascend-inference
An installation package for Ascend model conversion, quantization, inference deployment, and evaluation. It includes tools and guides for vLLM-Ascend, ais-bench, Diffusers, and related model workflows.