use-winml-cli Skill
Build, optimize, quantize, compile, and benchmark ONNX models for Windows ML using the winml CLI. Covers the Build-Your-Own-Model (BYOM) pipeline across NPU (Qualcomm QNN, Intel OpenVINO, AMD VitisAI), GPU, and CPU execution providers. Use this skill whenever the user wants to run a Hugging Face or ONNX model on a Wind Published by microsoft in winml-cli.
Decision snapshot
Is this a fit?
Developers using winml-cli, Includes SKILL.md, Reusable instructions
Compatibility not yet detected.
Permission behavior not yet detected.
Copy skill directory
2 months ago · MIT license
No specific cautions were detected. Review the source and requested permissions before installing.
What is use-winml-cli Skill?
Build, optimize, quantize, compile, and benchmark ONNX models for Windows ML using the winml CLI. Covers the Build-Your-Own-Model (BYOM) pipeline across NPU (Qualcomm QNN, Intel OpenVINO, AMD VitisAI), GPU, and CPU execution providers. Use this skill whenever the user wants to run a Hugging Face or ONNX model on a Wind Published by microsoft in winml-cli. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement. See how SkillIndex evaluates profiles.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Developers using winml-cli
Declared skill metadata
- Source file: skills/use-winml-cli/SKILL.md
These fields retain source and confidence evidence from the indexed SKILL.md.
Compatibility and setup
- Install or run with Copy skill directory
When to use use-winml-cli Skill
- Use it for developers using winml-cli.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/winml-cli
- Skill file: skills/use-winml-cli/SKILL.md
What it does
Build, optimize, quantize, compile, and benchmark ONNX models for Windows ML using the winml CLI. Covers the Build-Your-Own-Model (BYOM) pipeline across NPU (Qualcomm QNN, Intel OpenVINO, AMD VitisAI), GPU, and CPU execution providers. Use this skill whenever the user wants to run a Hugging Face or ONNX model on a Wind
Skill instructions
winml CLI winml is a CLI that turns a source model — a Hugging Face ID or a local ONNX file — into a portable, performant artifact that runs on any Windows execution provider. This skill teaches you the shape of that workflow. The CLI is the source of truth for current commands and flags. Installing the CLI Default behavior: lead any walkthrough with a brief install section. Unless the user signals they already have winml working, include the install steps below (or a clear "prereq: install winml first" pointer to them) as the first thing in your response. First-timers shouldn't have to guess what they need. Skip the install section only if the user clearly signals they're past install: - They quote a winml <command they ran, with output or an error from it. - They say they "already" / "previously" exported, built, optimized, etc. with winml. - They share an artifact path that came out of an earlier winml run. - They're asking a debugging or comparison question that presumes a working
Verified compatibility and discovery
Frequently asked questions
What is use-winml-cli?
use-winml-cli is a open-source AI agent skill with Copy skill directory. Build, optimize, quantize, compile, and benchmark ONNX models for Windows ML using the winml CLI.
Who is use-winml-cli best for?
use-winml-cli is best for reusing agent instructions, scripts, and references.
How do I install use-winml-cli?
Install or run use-winml-cli using Copy skill directory. Check use-winml-cli for the latest setup command.
Is use-winml-cli actively maintained?
use-winml-cli may need a closer maintenance check before production use.
Project health auto-fetched from the source repository.
Maintain this resource?
Review this source-backed profile, send a correction with evidence, or link to it from your documentation. Claims verify your relationship to the project; profile facts still require source evidence and editorial review.
