PR Review
pytorch/pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility.
Generate PyTorch release notes worksheet for XPU by searching git log between release branches.
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install intel/torch-xpu-ops xpu-release-notes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/xpu-release-notes .claude/skills/xpu-release-notes && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .claude/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install intel/torch-xpu-ops xpu-release-notes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/xpu-release-notes .agents/skills/xpu-release-notes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .agents/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install intel/torch-xpu-ops xpu-release-notes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/xpu-release-notes .cursor/skills/xpu-release-notes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .cursor/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/intel/torch-xpu-ops.git --path .claude/skills/xpu-release-notes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install intel/torch-xpu-ops xpu-release-notes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/xpu-release-notes .gemini/skills/xpu-release-notes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .gemini/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install intel/torch-xpu-ops xpu-release-notesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/xpu-release-notes .github/skills/xpu-release-notes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .github/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install intel/torch-xpu-ops xpu-release-notes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/xpu-release-notes .opencode/skills/xpu-release-notes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xpu-release-notes" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/xpu-release-notes into .opencode/skills/xpu-release-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xpu-release-notes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xpu-release-notesGenerate PyTorch release notes worksheet for XPU by searching git log between release branches.
Xpu Release Notes is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Generate PyTorch release notes worksheet for XPU by searching git log between release branches. Trigger on "xpu-release-notes", "generate XPU release notes".
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Changelog and release notes, Educational content and Deep learning. It works with PyTorch and Git. The licence is Apache-2.0.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 0187b3b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Xpu Release Notes loads about 1.1k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 463 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from intel/torch-xpu-ops at commit 0187b3b, republished under its Apache-2.0 licence (© intel). 463 words, ~1,070 tokens.
.claude/skills/xpu-release-notes/SKILL.md (or your agent's skills folder).Generate and complete the release notes worksheet for xpu.
/xpu-release-notes <version> <torch-release-notes-clone-path>Where <version> is the PyTorch release version (e.g., 2.11.0) and <torch-release-notes-clone-path> is the path to the cloned https://github.com/meta-pytorch/torch-release-notes repository.
torch-release-notes-clone-path/2.12.0/). If not, tell the user to update to latest main branch of torch-release-notes.<torch-release-notes-clone-path>/<version>/todo/result_xpu.md. If it's already in done/, tell the user it's already completed and ask if they want to re-process it.Fetch the previous and current release branches from the PyTorch repo:
git fetch origin release/<prev_version_minor>:release/<prev_version_minor> release/<current_version_minor>:release/<current_version_minor>For example, for version 2.12.0:
release/2.11release/2.12Search git log between the two release branches for commits related to xpu, and save the results to a <version>.txt for review. Use the following command:
git log --oneline origin/release/<prev>..origin/release/<current> | grep -Ei "xpu|sycl|oneapi|intel"<todo>/result_xpu.md to understand taskRead <torch-release-notes-clone-path>/<version>/todo/result_xpu.md worksheet file with the categorized commits. Follow the instructions in the worksheet to ensure proper categorization, clear descriptions, and formatting.
Reference previous version's completed notes to understand more about the categories and style.
<todo>/result_xpu.md worksheetFormat each entry as:
- Clear description of the change ([#NNNNN](https://github.com/pytorch/pytorch/pull/NNNNN))Grouping: Merge related PRs into a single entry when they implement the same logical change:
- Improve Inductor UT coverage for XPU ([#174053](https://github.com/pytorch/pytorch/pull/174053), [#174054](https://github.com/pytorch/pytorch/pull/174054), ...)Style rules:
torch.compile, conv2d, addmm[tag] prefixes — integrate the context into the descriptionWrite the complete worksheet to <version>/done/result_xpu.md (or <version>/todo/result_xpu.md if not yet finalized).
Present the categorized notes for user review. Common feedback patterns:
Iterate until the user is satisfied, then ensure the file is in done/.
For XPU, the search terms were xpu, sycl, oneapi, Intel GPU. The process found ~80 commits, which were filtered down to ~25 entries across categories. Key decisions:
torch.accelerator.Graph support → new feature (new API surface)© intel, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/xpu-release-notes of intel/torch-xpu-ops.
Open the folder on GitHubat commit 0187b3b
Xpu Release Notes next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xpu Release Notes this skillintel/torch-xpu-ops | 115 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| PR Reviewpytorch/pytorch | 104k | — | ~3.6k | Automated safety check: Pass | Custom licence | |
| Release Docs UpdateAMD-AGI/Primus | 130 | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Release Create Tracker Issuepytorch/test-infra | 113 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| React Router Release Notes Prepremix-run/react-router | 57k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Draft Release Notesjamiepine/voicebox | 57k | — | ~941 | Automated safety check: Pass | MIT |
pytorch/pytorch
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility.
AMD-AGI/Primus
Update the Primus documentation for a monthly training-image release — bump version references, realign the bare-metal install scripts with the release Dockerfiles, record the published image stacks…
pytorch/test-infra
Generate (and optionally open) a PyTorch release tracker / cherry-pick tracking issue from a release announcement, like https://github.com/pytorch/pytorch/issues/180506.
remix-run/react-router
Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.
jamiepine/voicebox
Writes or refreshes the Unreleased section of CHANGELOG.md as a themed narrative built from the commits, PRs and diff since the last version tag.
tw93/Mole
Publishes curated, bilingual release notes for an existing Mole version tag with gh release edit, including contributor thanks and reactions, after the release workflow finishes.
intel/torch-xpu-ops
Select the Intel GPU device to use when a system has multiple Intel GPU devices.
intel/torch-xpu-ops
Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…
intel/torch-xpu-ops
Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code.
intel/torch-xpu-ops
Review pull requests for XPU operator or backend code. An agent skill from intel/torch-xpu-ops.
intel/torch-xpu-ops
Guide users through creating Agent Skills for Claude Code. An agent skill from intel/torch-xpu-ops.
intel/torch-xpu-ops
Read the evidence a nightly UT run produced, decide which failures share a root cause and which are machine breakage rather than product bugs, and write one issue draft per root cause to drafts.json.
Categories
Generate PyTorch release notes worksheet for XPU by searching git log between release branches. Xpu Release Notes is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Generate PyTorch release notes worksheet for XPU by searching git log between release branches.
Xpu Release Notes fits situations like: xpu-release-notes; generate XPU release notes.
Run `npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a claude-code`. Or copy the skill folder (.claude/skills/xpu-release-notes in intel/torch-xpu-ops) into .claude/skills/xpu-release-notes in your project. Claude Code loads it when a task matches its description.
Run `npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a codex`. Or copy the skill folder (.claude/skills/xpu-release-notes in intel/torch-xpu-ops) into .agents/skills/xpu-release-notes in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add intel/torch-xpu-ops --skill xpu-release-notes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xpu-release-notes, .gemini/skills/xpu-release-notes, .github/skills/xpu-release-notes and .opencode/skills/xpu-release-notes in your project.
Going by SKILL.md and its folder, Xpu Release Notes needs the command-line tools its instructions call (git).
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Xpu Release Notes is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Xpu Release Notes: PR Review (pytorch/pytorch, 104k stars), Release Docs Update (AMD-AGI/Primus, 130 stars), Release Create Tracker Issue (pytorch/test-infra, 113 stars) and React Router Release Notes Prep (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
intel (a GitHub organization, an official publisher) maintains it in intel/torch-xpu-ops, which has 115 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 6, 2026.
Source: intel/torch-xpu-ops on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.