Official agent skill

Ut Check

Analyze UT (unit test) results for a torch-xpu-ops PR. An agent skill from intel/torch-xpu-ops.

OfficialApache-2.0Auto-check passedTesting & QA

Install Ut Check

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ut-check .claude/skills/ut-check && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .claude/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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

$skill-installer install https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check

Type 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.

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ut-check .agents/skills/ut-check && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .agents/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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.

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ut-check .cursor/skills/ut-check && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .cursor/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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

$ gemini skills install https://github.com/intel/torch-xpu-ops.git --path .claude/skills/ut-check

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ut-check .gemini/skills/ut-check && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .gemini/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check

Installs 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).

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ut-check .github/skills/ut-check && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .github/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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.

skills CLI

$ npx skills add intel/torch-xpu-ops --skill ut-check -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install intel/torch-xpu-ops ut-check --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/intel/torch-xpu-ops.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ut-check .opencode/skills/ut-check && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ut-check" agent skill from https://github.com/intel/torch-xpu-ops/tree/main/.claude/skills/ut-check into .opencode/skills/ut-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ut-check", 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.

Facts

Skill name: ut-check
GitHub stars: 115
Token cost: ~1.6k tokens
SKILL.md length: 641 words
Files: 1
Skills in repo: 29
Repo updated: Oct 6, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Analyze UT (unit test) results for a torch-xpu-ops PR. An agent skill from intel/torch-xpu-ops.

Works in 4 steps: Read the Data → Review / Refine Failure Relevance → Evaluate New Test Coverage → …
Asked to check test results
SKILL.md covers Quick start, Input, Analysis Workflow and Guardrails: Do Not Post…, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ut Check is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Analyze UT (unit test) results for a torch-xpu-ops PR. Use when asked to check test results, analyze CI failures, or evaluate test coverage for a PR. Produces a structured report of new failures, failure relevance, and new test coverage.

Its SKILL.md is about 1.6k 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 Testing & QA, covering Test coverage, Unit testing and Failing and flaky tests. The licence is Apache-2.0.

When your agent uses it

Asked to check test results
Analyze CI failures
Evaluate test coverage for a PR

Example prompts

“/ut-check”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Read the Data
Review / Refine Failure Relevance
Evaluate New Test Coverage
Produce the Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0187b3b. It shows what the files ask for, not the result of running them.

Tool permissions
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.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ut Check loads about 1.6k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 641 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~62
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from intel/torch-xpu-ops at commit 0187b3b, republished under its Apache-2.0 licence (© intel). 641 words, ~1,577 tokens.

Download SKILL.mdSave it as .claude/skills/ut-check/SKILL.md (or your agent's skills folder).

name: ut-check
description: Analyze UT (unit test) results for a torch-xpu-ops PR. Use when asked to check test results, analyze CI failures, or evaluate test coverage for a PR. Produces a structured report of new failures, failure relevance, and new test coverage.

UT Result Check Skill

Analyze unit test results for a torch-xpu-ops PR: identify new failures, assess whether they relate to the PR changes, and verify new test coverage.

Quick start

Read the UT data JSON at the path given in the request (default /tmp/ut_data.json). If it is missing or unreadable, say so and stop -- never reconstruct the data from elsewhere.
Analyze it following the workflow below. The data is self-contained; no sub-agents or extra CI queries are needed.
Emit the report as your final message. The calling workflow posts it as the PR comment -- do not post a comment yourself.

Input

The UT data is provided as a JSON file (typically /tmp/ut_data.json) produced by .github/scripts/bot_ut_check.py. The script already de-duplicates failures, classifies each failure's relevance, summarizes new-test coverage, and computes a baseline verdict. The JSON contains:

json

{
  "pr_number": 1234,
  "run_id": 56789,
  "failures": [
    {"category": "op_ut", "class": "a.b.TestFoo", "test": "test_bar",
     "status": "failed", "message": "...", "relevance": "Related"}
  ],
  "changed_files": {
    "operator_source": ["src/ATen/native/xpu/Foo.cpp"],
    "test_files": ["test/xpu/test_foo_xpu.py"],
    "skip_lists": [],
    "other": []
  },
  "new_tests": ["TestFoo::test_bar"],
  "new_tests_summary": {
    "passed": ["TestFoo::test_bar"],
    "failed": [],
    "skipped": [],
    "not_run": []
  },
  "passed_tests_count": 12345,
  "totals": {"test_cases": 0, "passed": 0, "skipped": 0,
             "failures": 0, "errors": 0},
  "verdict": "Safe to merge",
  "verdict_reason": "No new failures detected."
}

Ground Truth for New Failures

The authoritative source for new failures is the New-UT-Failures-* artifact which contains new_ut_failure_list.csv. This CSV is produced by the CI summary job: ut_result_check.sh identifies new failures (not in the known issues list), and the workflow enriches them with error messages.

The Inductor-XPU-UT-Data-* artifact bundles a duplicate copy of that CSV; bot_ut_check.py reads only the authoritative artifact and de-duplicates by (category, class, test). If you ever see the same failure listed twice, treat it as a single failure and note the collection anomaly.

Analysis Workflow

Step 1: Read the Data

Read the JSON. Understand the scope: failure count, changed files, new tests.

Step 2: Review / Refine Failure Relevance

Each failure already carries a deterministic relevance (Related / Possibly related / Unrelated) computed from the changed files. Trust it as a baseline, but refine using the error message and your judgment:

Related -- failure is in a test module that directly tests an operator or test file this PR modifies.
Possibly related -- failure is in a related subsystem or a plausible side effect of the change.
Unrelated -- failure is in an unrelated module; likely pre-existing flake or infrastructure issue (e.g. missing shared library, download error).

If you change a classification, briefly say why.

Step 3: Evaluate New Test Coverage

Use new_tests_summary: passed, failed, skipped, not_run. Newly added tests that FAILED or did NOT RUN are a concern and must be called out.

Step 4: Produce the Report

Follow the output format below exactly. Apply the truncation rules strictly.

Show full SKILL.md (255 more words)Show less

Guardrails: Do Not Post Low-Quality Comments

Never fabricate or guess counts. Report exactly what the JSON contains.
If failures is empty and new_tests is empty, produce a concise report (New Failures: none; Recommendation) rather than padding with empty tables.
If the data looks internally inconsistent (e.g. a failure count that seems implausible for the diff, or totals missing), state the uncertainty plainly in the Recommendation instead of asserting a confident verdict.
Do not invent a "Failure Relevance Analysis" for failures that are all clearly unrelated; a one-line grouping is enough.

Truncation Rules

New failures: If more than 20, show the first 20, then add: ... and N more failure(s). See CI logs for the full list.
New/modified tests: If more than 20, show the first 20, then add: ... and N more new test(s). See CI logs for the full list.
Changed files: Summarize as counts per category.

Always include the total count so the reader knows the full scope.

Output Format

Every report MUST include: the New Failures section (with the Related to PR? column), a New Test Coverage summary line with counts whenever the PR adds tests, and a Recommendation with an explicit safe-to-merge verdict.

markdown

## UT Result Check: PR #<number>

### New Failures
<count> new failure(s) detected (not in known issues). / No new failures detected.

| Test | Category | Status | Related to PR? |
|------|----------|--------|----------------|
| `ClassName::test_name` | category | failed | Related / Possibly related / Unrelated |
...

### Failure Relevance Analysis
Brief explanation, grouping related failures together. Omit if there are no
failures or all are trivially unrelated (a one-line note then suffices).

### New Test Coverage
This PR adds/modifies **<N>** test(s): <p> passed, <f> failed, <s> skipped, <n> not run.

| New/Modified Test | Status |
|-------------------|--------|
| `ClassName::test_name` | PASSED / FAILED / SKIPPED / NOT RUN |
...

### Recommendation
**<Safe to merge | Likely safe to merge | Investigate before merging | Not safe to merge>.**
One-to-two sentence justification grounded in the failures and new-test results.

Omit sections that have no content. If the PR adds no tests, omit "New Test Coverage". Always keep the "New Failures" and "Recommendation" sections.

If a calling workflow explicitly requires a skill marker, append this exact literal final line: Custom skills applied: ut-check.

Otherwise, keep the reply in the requested report format and do not force an extra trailing sentence.

Files

Just SKILL.md in .claude/skills/ut-check of intel/torch-xpu-ops.

Open the folder on GitHubat commit 0187b3b

Compare with similar skills

Ut Check 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.

Ut Check compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Ut Check this skillintel/torch-xpu-ops	115	—	~1.6k	Automated safety check: Pass	Apache-2.0	yesterday
Test Suite Curationpetrkindlmann/qa-skills	163	—	~6.3k	Automated safety check: Pass	MIT	3 mo ago
Caliber Testingcaliber-ai-org/ai-setup	1.3k	—	~3.2k	Automated safety check: Pass	MIT	13 days ago
LobeHub Testing Guidelobehub/lobehub	83k	—	~1.6k	Automated safety check: Pass	Custom licence	today
Squid Testing Pythoniusztinpaul/squid	203	—	~1.3k	Automated safety check: Pass	Apache-2.0	1 mo ago
Sf TestingJaganpro/sf-skills	424	—	~1.1k	Automated safety check: Pass	MIT	5 mo ago

Similar skills

Test Suite Curation
petrkindlmann/qa-skills
Audit a whole regression suite and prune/restructure it with evidence: per-test coverage fingerprinting, AST near-duplicate clustering, CI-history mining for never-failing and flaky tests, prune…
163 GitHub stars~6.3k tokensUpdated 3 mo ago
Testing & QAAuto-check passed
Caliber Testing
caliber-ai-org/ai-setup
Writes Vitest tests following project patterns: tests/ directories, vi.mock() for module mocking with vi.hoisted() for test-time factories, global LLM mock from src/test/setup.ts, environment…
1.3k GitHub stars~3.2k tokensUpdated 13 days ago
Testing & QAAuto-check passed
LobeHub Testing Guide
lobehub/lobehub
Explains how to write and run Vitest tests in the LobeHub monorepo: single-file commands, mocking rules, database model tests and regression tests for fixes.
83k GitHub stars~1.6k tokensUpdated today
Testing & QAAuto-check passed
Squid Testing Python
iusztinpaul/squid
Write and evaluate effective Python tests using pytest. An agent skill from iusztinpaul/squid.
203 GitHub stars~1.3k tokensUpdated 1 mo ago
Testing & QAAuto-check passed
Sf Testing
Jaganpro/sf-skills
Apex test execution, coverage analysis, and test-fix loops with 120-point scoring.
424 GitHub stars~1.1k tokensUpdated 5 mo ago
Testing & QAAuto-check passed
Platform Apex Test Run
forcedotcom/sf-skills
Apex test execution, coverage analysis, and test-fix loops with 120-point scoring.
1.1k GitHub stars~1.9k tokensUpdated 4 days ago
Testing & QAAuto-check passed

More from intel/torch-xpu-ops

All 29 skills in this repo

Intel GPU Device Selection
intel/torch-xpu-ops
Official
Select the Intel GPU device to use when a system has multiple Intel GPU devices.
115 GitHub stars~508 tokensUpdated yesterday
Auto-check passed
Xpu CI Health Check
intel/torch-xpu-ops
Official
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…
115 GitHub stars~1.5k tokensUpdated yesterday
Auto-check passed
At Dispatch V2
intel/torch-xpu-ops
Official
Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code.
115 GitHub starsUsed in 3 repos~2.2k tokens
Auto-check passed
PR Review
intel/torch-xpu-ops
Official
Review pull requests for XPU operator or backend code. An agent skill from intel/torch-xpu-ops.
115 GitHub stars~4.2k tokensUpdated yesterday
Auto-check passed
Skill Writer
intel/torch-xpu-ops
Official
Guide users through creating Agent Skills for Claude Code. An agent skill from intel/torch-xpu-ops.
115 GitHub starsUsed in 3 repos~2.4k tokens
Auto-check passed
Ut Issue Authoring
intel/torch-xpu-ops
Official
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.
115 GitHub stars~2k tokensUpdated yesterday
Auto-check passed

Questions about Ut Check

What does Ut Check do?

Analyze UT (unit test) results for a torch-xpu-ops PR. An agent skill from intel/torch-xpu-ops. Ut Check is an agent skill from intel/torch-xpu-ops, published by the product's own GitHub organization. Analyze UT (unit test) results for a torch-xpu-ops PR.

When should I use Ut Check?

Ut Check fits situations like: asked to check test results; analyze CI failures; evaluate test coverage for a PR.

How do I install Ut Check in Claude Code?

Run `npx skills add intel/torch-xpu-ops --skill ut-check -a claude-code`. Or copy the skill folder (.claude/skills/ut-check in intel/torch-xpu-ops) into .claude/skills/ut-check in your project. Claude Code loads it when a task matches its description.

How do I install Ut Check in Codex?

Run `npx skills add intel/torch-xpu-ops --skill ut-check -a codex`. Or copy the skill folder (.claude/skills/ut-check in intel/torch-xpu-ops) into .agents/skills/ut-check in your project. Codex loads it when a task matches its description.

Can I use Ut Check in Cursor, Gemini CLI or GitHub Copilot?

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 ut-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ut-check, .gemini/skills/ut-check, .github/skills/ut-check and .opencode/skills/ut-check in your project.

What does Ut Check need to run?

SKILL.md names no scripts, command-line tools or credentials: Ut Check is instructions for the agent only.

Does Ut Check access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ut Check safe to install?

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.

What licence does Ut Check use?

Ut Check 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.

How many tokens does Ut Check use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ut Check?

Skills that share tags, products or a category with Ut Check: Test Suite Curation (petrkindlmann/qa-skills, 163 stars), Caliber Testing (caliber-ai-org/ai-setup, 1.3k stars), LobeHub Testing Guide (lobehub/lobehub, 83k stars) and Squid Testing Python (iusztinpaul/squid, 203 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ut Check?

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.

Install Ut Check

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

UT Result Check Skill

Quick start

Input

Ground Truth for New Failures

Analysis Workflow

Step 1: Read the Data

Step 2: Review / Refine Failure Relevance

Step 3: Evaluate New Test Coverage

Step 4: Produce the Report

Guardrails: Do Not Post Low-Quality Comments

Truncation Rules

Output Format

Files

Compare with similar skills

Similar skills

More from intel/torch-xpu-ops

Related

Questions about Ut Check