Agent skill

Scrub Issue

by pytorch in pytorch/pytorch

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

Custom licenceAuto-check passedTesting & QA

Install Scrub Issue

skills CLI
$ npx skills add pytorch/pytorch --skill scrub-issue -a claude-code

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

GitHub CLI
$ gh skill install pytorch/pytorch scrub-issue --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/pytorch/pytorch.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/scrub-issue .claude/skills/scrub-issue && 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/

Facts

Skill name
scrub-issue
GitHub stars
104k
Token cost
~4.6k tokens
SKILL.md length
2,638 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
Custom licence

At a glance

Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

  • Works in 8 steps: Fetch the issue → Check if the issue is actionable → Analyze the repro → …
  • Asks to check whether a GitHub issue reproduces
  • SKILL.md covers Tools and Steps
  • Calls gh, python and conda

What it does

Scrub Issue is an agent skill from pytorch/pytorch. Fetch, analyze, reproduce, and minimize GitHub issue reproductions. Use only when the user asks to check whether a GitHub issue reproduces, minimize a GitHub issue's repro, analyze a GitHub bug report, or scrub/triage a GitHub issue for reproducibility. Do not use for standalone reproduction requests without a GitHub issue.

Its SKILL.md is about 4.6k 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 QA and bug reports, Deep learning and Reproducible research. It works with GitHub and PyTorch. The repository describes itself as: Tensors and Dynamic neural networks in Python with strong GPU acceleration.

When your agent uses it

  • Asks to check whether a GitHub issue reproduces
  • Minimize a GitHub issues repro
  • Analyze a GitHub bug report
  • Scrub/triage a GitHub issue for reproducibility

Example prompts

  • “/scrub-issue”

Requirements

  • Python 3

Workflow steps

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

  1. Fetch the issue
  2. Check if the issue is actionable
  3. Analyze the repro
  4. Check for recent verification
  5. Check if it still reproduces
  6. Minimize the repro
  7. Apply trivial fixes
  8. Report findings

What it can do on your machine

Read from SKILL.md and the folder at commit 84af535. 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

    Shell commands in SKILL.md call:

    • gh
    • python
    • conda

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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

Scrub Issue loads about 4.6k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 2,638 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 2,638 words (~4,634 tokens).

“Fetch a GitHub issue, evaluate whether it has a reasonable repro, check if it still reproduces, and systematically minimize the repro to the smallest possible self-contained script.”

— opening of SKILL.md by pytorch, Custom licence
name
scrub-issue
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/scrub-issue of pytorch/pytorch.

Open the folder on GitHubat commit 84af535

Compare with similar skills

Scrub Issue 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.

Scrub Issue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scrub Issue this skillpytorch/pytorch104k—~4.6kAutomated safety check: PassCustom licence
Homepage Generatorwanshuiyin/ARIS-in-AI-Offer574—~4.8kAutomated safety check: NotesMIT
Release Cherry Pick Missing Revertspytorch/test-infra113—~2.6kAutomated safety check: PassCustom licence
Release Create Tracker Issuepytorch/test-infra113—~2.7kAutomated safety check: PassCustom licence
Release Create Validation Issuepytorch/test-infra113—~2.2kAutomated safety check: PassCustom licence
Release Update Docker Image Pinpytorch/test-infra113—~2.1kAutomated safety check: PassCustom licence

Similar skills

  • Homepage Generator

    wanshuiyin/ARIS-in-AI-Offer

    Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory.

    574 GitHub stars~4.8k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Find reverts that landed on pytorch/pytorch main but are missing from a release branch (release/X.Y) because the reverted commit was already shipped in a release candidate, and open one cherry-pick…

    113 GitHub stars~2.6k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Generate (and optionally open) a PyTorch release tracker / cherry-pick tracking issue from a release announcement, like https://github.com/pytorch/pytorch/issues/180506.

    113 GitHub stars~2.7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Generate a PyTorch release validation checklist issue by pulling open/closed issues from a GitHub milestone and cherry-picks from a release tracker issue.

    113 GitHub stars~2.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Pin (or re-pin) the Linux manywheel builder docker images used by the nightly/release binary build workflows in pytorch/pytorch to a fixed .ci/docker build.

    113 GitHub stars~2.1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Matlab Integrate Pytorch Vision

    matlab/matlab-agentic-toolkit

    Creates MATLAB interfaces to Python image processing and computer vision models from GitHub repositories or pip-installable packages using MPyReq.

    1.1k GitHub stars~3.7k tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

More from pytorch/pytorch

All 16 skills in this repo
  • Add Uint Support

    pytorch/pytorch

    Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

    104k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Docstring

    pytorch/pytorch

    Write docstrings for PyTorch functions and methods following PyTorch conventions.

    104k GitHub starsUsed in 2 repos~2.6k tokens
    Auto-check passed
  • Aoti Debug

    pytorch/pytorch

    Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

    104k GitHub starsUsed in 1 repo~1.7k tokens
    Auto-check passed
  • CI Metrics

    pytorch/pytorch

    Query PyTorch CI, GitHub Actions, HUD, Grafana, and infrastructure metrics.

    104k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Cuda Index Width

    pytorch/pytorch

    Choose 32-bit vs 64-bit index math in PyTorch CUDA kernels. An agent skill from pytorch/pytorch.

    104k GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Document Public APIs

    pytorch/pytorch

    Document undocumented public APIs in PyTorch by removing functions from coverageignorefunctions and coverageignoreclasses in docs/source/conf.py, running Sphinx coverage, and adding the appropriate…

    104k GitHub stars~4.2k tokensUpdated today
    Auto-check passed

Works with

Questions about Scrub Issue

What does Scrub Issue do?

Fetch, analyze, reproduce, and minimize GitHub issue reproductions. Scrub Issue is an agent skill from pytorch/pytorch. Fetch, analyze, reproduce, and minimize GitHub issue reproductions.

When should I use Scrub Issue?

Scrub Issue fits situations like: asks to check whether a GitHub issue reproduces; minimize a GitHub issues repro; analyze a GitHub bug report; scrub/triage a GitHub issue for reproducibility.

How do I install Scrub Issue in Claude Code?

Run `npx skills add pytorch/pytorch --skill scrub-issue -a claude-code`. Or copy the skill folder (.agents/skills/scrub-issue in pytorch/pytorch) into .claude/skills/scrub-issue in your project. Claude Code loads it when a task matches its description.

How do I install Scrub Issue in Codex?

Run `npx skills add pytorch/pytorch --skill scrub-issue -a codex`. Or copy the skill folder (.agents/skills/scrub-issue in pytorch/pytorch) into .agents/skills/scrub-issue in your project. Codex loads it when a task matches its description.

Can I use Scrub Issue 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 pytorch/pytorch --skill scrub-issue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scrub-issue, .gemini/skills/scrub-issue, .github/skills/scrub-issue and .opencode/skills/scrub-issue in your project.

What does Scrub Issue need to run?

Going by SKILL.md and its folder, Scrub Issue needs the command-line tools its instructions call (gh, python and conda). Our summary lists: Python 3.

Does Scrub Issue access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scrub Issue 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 Scrub Issue use?

Scrub Issue has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Scrub Issue use?

About 4.6k tokens (SKILL.md is roughly 19k 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 Scrub Issue?

Skills that share tags, products or a category with Scrub Issue: Homepage Generator (wanshuiyin/ARIS-in-AI-Offer, 574 stars), Release Cherry Pick Missing Reverts (pytorch/test-infra, 113 stars), Release Create Tracker Issue (pytorch/test-infra, 113 stars) and Release Create Validation Issue (pytorch/test-infra, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scrub Issue?

pytorch (a GitHub organization) maintains it in pytorch/pytorch, which has 103,819 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 7, 2026.

Source: pytorch/pytorch on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.