How do I install the Ut Refactor Review skill?

Run npx skillmds@latest add intel/ut-refactor-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ut Refactor Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ut Refactor Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ut Refactor Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ut Refactor Review?

intel (@intel) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ut Refactor Review by intel — Agent Skill

Name: Ut Refactor Review
Author: intel

Ut Refactor Review

Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests. Use when reviewing PRs under test/ that port device-generic tests to XPU, add allow_xpu=True, generalize CUDA-hardcoded tests, or add XPU skips/xfails/tolerance overrides in OpInfo.

intel 55cee60 2 files · 5.4 KB Updated Sep 17, 2026

File contents

XPU UT Refactor Review Skill

Review PyTorch (pytorch/pytorch) pull requests that enable XPU on existing upstream unit tests. These PRs almost never add new operator logic; they make existing tests device-agnostic and opt XPU into them. The review must focus on what CI cannot check: whether the generalization preserves the original test intent, whether device gating is precise, and whether every skip/xfail is justified and traceable.

Scope: when this skill applies

Use this skill (instead of the generic pr-review skill in pytorch/pytorch) when the diff is predominantly:

test/** changes that swap CUDA-hardcoded constructs for device-generic ones
instantiate_device_type_tests(..., allow_xpu=True) additions
onlyAccelerator / onlyNativeDeviceTypesAnd([...]) decorator migrations
XPU entries in OpInfo (common_methods_invocations.py, opinfo/definitions/*): DecorateInfo(... device_type='xpu' ...), toleranceOverride, skips, xfails
New TestXxxDevice classes split out from a device-agnostic TestXxx

If the PR also changes operator kernels or native_functions.yaml, hand those files to the pr-review skill and apply this skill only to the test files.

Usage Modes

No Argument

If invoked with no arguments, do not review. Ask:

What would you like me to review?

A PR number or URL (e.g., 159118 or the full PR URL)

A local branch

PR Mode

/ut-refactor-review 159118
/ut-refactor-review https://github.com/pytorch/pytorch/pull/159118
/ut-refactor-review 159118 detailed

Obtain the PR title, description, diff, changed-file list, and existing review comments before reviewing. If the command does not name a repo, default to fetching the PR from pytorch/pytorch.

Suggested fetch commands (CLI environments with gh):

gh pr view <PR_NUMBER> --repo pytorch/pytorch --json title,body,author,baseRefName,headRefName,files,additions,deletions,commits
gh pr diff <PR_NUMBER> --repo pytorch/pytorch
gh pr view <PR_NUMBER> --repo pytorch/pytorch --json comments,reviews

Local Branch Mode

/ut-refactor-review branch
/ut-refactor-review branch detailed

Review the current branch's changes relative to main (diff, commit log, and changed-file list). Use the branch name in the review header instead of a PR number.

Review Philosophy

Go through every changed line against references/xpu-ut-review-checklist.md. For anything this skill does not address, defer to the pr-review skill in pytorch/pytorch.

Files to Reference

references/xpu-ut-review-checklist.md — the line-by-line checklist
torch/testing/_internal/common_device_type.py — instantiate_device_type_tests, onlyAccelerator, allow_xpu, only_for
torch/testing/_internal/common_utils.py — TEST_XPU, TEST_CUDA, TEST_HPU, xfailIf, HardwareClassification
torch/testing/_internal/common_methods_invocations.py, torch/testing/_internal/opinfo/definitions/* — OpInfo DecorateInfo, toleranceOverride

---name: ut-refactor-reviewdescription: Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests. Use when reviewing PRs under test/ that port device-generic tests to XPU, add allow_xpu=True, generalize CUDA-hardcoded tests, or add XPU skips/xfails/tolerance overrides in OpInfo.---# XPU UT Refactor Review SkillReview PyTorch (`pytorch/pytorch`) pull requests that **enable XPU on existingupstream unit tests**. These PRs almost never add new operator logic; they makeexisting tests device-agnostic and opt XPU into them. The review must focus onwhat CI cannot check: whether the generalization preserves the original testintent, whether device gating is precise, and whether every skip/xfail isjustified and traceable.## Scope: when this skill appliesUse this skill (instead of the generic [`pr-review`](https://github.com/pytorch/pytorch/blob/main/.claude/skills/pr-review/SKILL.md)skill in `pytorch/pytorch`) when the diff is predominantly:- `test/**` changes that swap CUDA-hardcoded constructs for device-generic ones- `instantiate_device_type_tests(..., allow_xpu=True)` additions- `onlyAccelerator` / `onlyNativeDeviceTypesAnd([...])` decorator migrations- XPU entries in OpInfo (`common_methods_invocations.py`, `opinfo/definitions/*`): `DecorateInfo(... device_type='xpu' ...)`, `toleranceOverride`, skips, xfails- New `TestXxxDevice` classes split out from a device-agnostic `TestXxx`If the PR also changes operator kernels or `native_functions.yaml`, hand thosefiles to the [`pr-review`](https://github.com/pytorch/pytorch/blob/main/.claude/skills/pr-review/SKILL.md)skill and apply this skill only to the test files.## Usage Modes### No ArgumentIf invoked with no arguments, **do not review**. Ask:> What would you like me to review?> - A PR number or URL (e.g., `159118` or the full PR URL)> - A local branch### PR Mode```/ut-refactor-review 159118/ut-refactor-review https://github.com/pytorch/pytorch/pull/159118/ut-refactor-review 159118 detailed```Obtain the PR title, description, diff, changed-file list, and existing reviewcomments before reviewing. If the command does not name a repo, default tofetching the PR from `pytorch/pytorch`.Suggested fetch commands (CLI environments with `gh`): gh pr view <PR_NUMBER> --repo pytorch/pytorch --json title,body,author,baseRefName,headRefName,files,additions,deletions,commits gh pr diff <PR_NUMBER> --repo pytorch/pytorch gh pr view <PR_NUMBER> --repo pytorch/pytorch --json comments,reviews### Local Branch Mode```/ut-refactor-review branch/ut-refactor-review branch detailed```Review the current branch's changes relative to `main` (diff, commit log, andchanged-file list). Use the branch name in the review header instead of a PRnumber.## Review PhilosophyGo through **every changed line** against[references/xpu-ut-review-checklist.md](references/xpu-ut-review-checklist.md).For anything this skill does not address, defer to the[`pr-review`](https://github.com/pytorch/pytorch/blob/main/.claude/skills/pr-review/SKILL.md)skill in `pytorch/pytorch`.## Files to Reference- [references/xpu-ut-review-checklist.md](references/xpu-ut-review-checklist.md) — the line-by-line checklist- `torch/testing/_internal/common_device_type.py` — `instantiate_device_type_tests`, `onlyAccelerator`, `allow_xpu`, `only_for`- `torch/testing/_internal/common_utils.py` — `TEST_XPU`, `TEST_CUDA`, `TEST_HPU`, `xfailIf`, `HardwareClassification`- `torch/testing/_internal/common_methods_invocations.py`, `torch/testing/_internal/opinfo/definitions/*` — OpInfo `DecorateInfo`, `toleranceOverride`

Frequently asked questions