Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer.
$ npx skills add pytorch/test-infra --skill vllm-upstream-dedup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pytorch/test-infra vllm-upstream-dedup --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/pytorch/test-infra.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .claude/skills/vllm-upstream-dedup && 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 "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .claude/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedupType 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 pytorch/test-infra --skill vllm-upstream-dedup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pytorch/test-infra vllm-upstream-dedup --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/test-infra.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .agents/skills/vllm-upstream-dedup && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .agents/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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 pytorch/test-infra --skill vllm-upstream-dedup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pytorch/test-infra vllm-upstream-dedup --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/test-infra.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .cursor/skills/vllm-upstream-dedup && 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 "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .cursor/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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/pytorch/test-infra.git --path .claude/skills/vllm-upstream-dedup--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 pytorch/test-infra --skill vllm-upstream-dedup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pytorch/test-infra vllm-upstream-dedup --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/test-infra.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .gemini/skills/vllm-upstream-dedup && 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 "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .gemini/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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 pytorch/test-infra vllm-upstream-dedupInstalls 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 pytorch/test-infra --skill vllm-upstream-dedup -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pytorch/test-infra.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .github/skills/vllm-upstream-dedup && 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 "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .github/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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 pytorch/test-infra --skill vllm-upstream-dedup -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pytorch/test-infra vllm-upstream-dedup --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pytorch/test-infra.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/vllm-upstream-dedup .opencode/skills/vllm-upstream-dedup && 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 "vllm-upstream-dedup" agent skill from https://github.com/pytorch/test-infra/tree/main/.claude/skills/vllm-upstream-dedup into .opencode/skills/vllm-upstream-dedup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "vllm-upstream-dedup", 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.
vllm-upstream-dedupReview vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer.
Vllm Upstream Dedup is an agent skill from pytorch/test-infra. Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer. Use in the vLLM torch-nightly triage workflow after root-cause analysis.
Its SKILL.md is about 1.3k 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 AI & LLM Engineering, covering LLM inference and serving and Root cause analysis. It works with vLLM, PyTorch and GitHub. The repository describes itself as: This repository hosts code that supports the testing infrastructure for the PyTorch organization. For example, this repo hosts the logic to track disabled tests and slow tests…
Read from SKILL.md and the folder at commit 5873748. 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:
curlFrom 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:
api.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.
Vllm Upstream Dedup loads about 1.3k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 578 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.
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 578 words (~1,288 tokens).
“Review the complete root-cause findings from one vLLM torch-nightly triage run before the filer creates any pytorch/test-infra issue. This is an evidence review step, not an issue-filing step.”
Just SKILL.md in .claude/skills/vllm-upstream-dedup of pytorch/test-infra.
Open the folder on GitHubat commit 5873748
Vllm Upstream Dedup 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 |
|---|---|---|---|---|---|---|
| Vllm Upstream Dedup this skillpytorch/test-infra | 113 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Ascend Release Manager for vLLMvllm-project/vllm-ascend | 2.9k | — | ~7.2k | Automated safety check: Pass | Apache-2.0 | |
| Graphsignalgraphsignal/graphsignal | 257 | — | ~6.2k | Automated safety check: Pass | Apache-2.0 | |
| Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel | 1.3k | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Hqq QuantizationOrchestra-Research/AI-Research-SKILLs | 13k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Magpie Kernel Evaluatoramd/skills | 406 | — | ~2.3k | Automated safety check: Pass | MIT |
vllm-project/vllm-ascend
Runs the end-to-end vLLM Ascend release process: opens the release checklist and feedback issues, scans for release-blocking bugs and test coverage gaps, and generates release notes and announcements.
graphsignal/graphsignal
Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.
ModelCloud/GPTQModel
Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.
Orchestra-Research/AI-Research-SKILLs
Half-Quadratic Quantization for LLMs without calibration data.
amd/skills
Benchmarks LLM inference and drives GPU kernel optimization with Magpie.
wshobson/agents
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).
pytorch/test-infra
Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…
pytorch/test-infra
Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.
pytorch/test-infra
Disable or re-enable Cloudflare R2 (download-r2.pytorch.org) usage in managev2.py during R2 outages.
pytorch/test-infra
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…
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.
pytorch/test-infra
Generate a PyTorch release validation checklist issue by pulling open/closed issues from a GitHub milestone and cherry-picks from a release tracker issue.
Categories
Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer. Vllm Upstream Dedup is an agent skill from pytorch/test-infra. Review vLLM-routed torch-nightly root causes against existing upstream vLLM issues using read-only search results, and emit a validated upstream-checks artifact for the filer.
Vllm Upstream Dedup fits situations like: tasks that involve LLM inference and serving; tasks that involve Root cause analysis.
Run `npx skills add pytorch/test-infra --skill vllm-upstream-dedup -a claude-code`. Or copy the skill folder (.claude/skills/vllm-upstream-dedup in pytorch/test-infra) into .claude/skills/vllm-upstream-dedup in your project. Claude Code loads it when a task matches its description.
Run `npx skills add pytorch/test-infra --skill vllm-upstream-dedup -a codex`. Or copy the skill folder (.claude/skills/vllm-upstream-dedup in pytorch/test-infra) into .agents/skills/vllm-upstream-dedup 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 pytorch/test-infra --skill vllm-upstream-dedup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vllm-upstream-dedup, .gemini/skills/vllm-upstream-dedup, .github/skills/vllm-upstream-dedup and .opencode/skills/vllm-upstream-dedup in your project.
Going by SKILL.md and its folder, Vllm Upstream Dedup needs the command-line tools its instructions call (curl). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: api.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.
Vllm Upstream Dedup has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Vllm Upstream Dedup: Ascend Release Manager for vLLM (vllm-project/vllm-ascend, 2.9k stars), Graphsignal (graphsignal/graphsignal, 257 stars), Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars) and Hqq Quantization (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
pytorch (a GitHub organization) maintains it in pytorch/test-infra, which has 113 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.
Source: pytorch/test-infra on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
