New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Vllm Metax Upgrade Common

by MetaX-MACA in MetaX-MACA/vLLM-metax

Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Vllm Metax Upgrade Common

skills CLI
$ npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-upgrade-common -a claude-code

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

GitHub CLI
$ gh skill install MetaX-MACA/vLLM-metax vllm-metax-upgrade-common --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/MetaX-MACA/vLLM-metax.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/vllm-metax-upgrade-common .claude/skills/vllm-metax-upgrade-common && 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
vllm-metax-upgrade-common
GitHub stars
180
Token cost
~1.1k tokens
SKILL.md length
523 words
Files
3 (incl. scripts, references)
Skills in repo
6
Repo updated
First seen
Licence
Apache-2.0

At a glance

Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades.

  • Tasks that involve LLM inference and serving
  • SKILL.md covers Environment and target and Shared scope and verification…
  • Runs Python scripts from its folder

What it does

Vllm Metax Upgrade Common is an agent skill from MetaX-MACA/vLLM-metax. Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades. Use as the common prerequisite of the patch, attention, registry and model upgrade skills, or for an explicitly requested MetaX environment preflight; it does not perform domain-specific adaptations.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/environment-preflight.md` and `scripts/probe_environment.py`).

It sits in AI & LLM Engineering, covering LLM inference and serving. It works with vLLM. The repository describes itself as: Community maintained hardware plugin for vLLM on MetaX GPU. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve LLM inference and serving

Example prompts

  • “/vllm-metax-upgrade-common”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit df0f52b. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    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

Vllm Metax Upgrade Common loads about 1.1k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 523 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.5k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from MetaX-MACA/vLLM-metax at commit df0f52b, republished under its Apache-2.0 licence (© MetaX-MACA). 523 words, ~1,128 tokens.

Download SKILL.mdSave it as .claude/skills/vllm-metax-upgrade-common/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
vllm-metax-upgrade-common
description
Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades. Use as the common prerequisite of the patch, attention, registry and model upgrade skills, or for an explicitly requested MetaX environment preflight; it does not perform domain-specific adaptations.

vLLM-MetaX Upgrade Common

Provide one shared baseline for specialist upgrade workflows. Read this skill when a calling skill requires it; apply only the common checks here, then continue that skill's domain workflow. Do not activate other specialist skills automatically.

Environment and target

Run the read-only environment preflight using this skill's scripts/probe_environment.py and the user-selected interpreter. It owns the five-location mapping, component inventory, content comparison and effective runtime-origin checks. Specialist skills must not copy the probe or maintain their own preflight instructions. Examples use /opt/venv/bin/python; discover actual paths.

Proactively confirm the comparison/runtime mapping once if it has not already been established in this session. Reuse unchanged confirmation across all calling skills; honor an explicit instruction to skip the question. A switch from patch to model work alone does not require confirmation again. Expected local edits do not invalidate the mapping. Ask again only when the intended interpreter, target or runtime mapping changes or becomes uncertain. If this requirement causes a pause, link this SKILL.md, quote this instruction and explain the concrete unresolved mapping.

Continue independent inventory while awaiting a required target choice. Do not treat silence, elapsed time or successful probe execution as confirmation. This is target clarification, not renewed permission for already authorized work.

Keep one reusable task record containing:

  • Selected interpreter/venv and runtime cwd.
  • Local vLLM target revision, installed vLLM identity and relevant content differences.
  • Local MetaX snapshot (index/worktree/revision), installed identity and effective imports.
  • Component versions, selected callable/extension origins and device/ABI evidence.
  • Intended comparison source, edited checkout and actual validation imports.
  • Confirmed choices or the user's instruction to skip confirmation; remaining unknowns.

Use the established target, not assumed remote HEAD. Version strings alone cannot prove correspondence. The probe is read-only and standard-library-only; exit zero means collection succeeded, not that APIs, binaries or numerical behavior are valid.

Show full SKILL.md (226 more words)Show less

Shared scope and verification rules

  • Preserve user changes. Keep reviews read-only. Do not stage, commit, reinstall, alter global import paths, edit upstream/site-packages or send external messages unless the task authorizes it. The calling skill sets the adaptation scope.
  • Identify the exact snapshot. For staged reviews, export the index and prove that validation imports it; unstaged fixes must not satisfy staged dependencies silently.
  • Trace actual plugin dispatch, wrappers and installed callables. Source comments, matching signatures and upstream capability declarations are hypotheses to verify.
  • For now, generate self-contained temporary validation scripts from current contracts; do not depend on repository tests/, its fixtures/helpers/conftest or historical /tmp files. Select meaningful cases in the calling skill's validation guidance.
  • Record commands, inputs, expected/observed behavior, imported sources, component identities and process-local workarounds. Isolated mocks test only the isolated contract; kernel tests do not establish full-model or distributed correctness.
  • Distinguish source inspection, signature checking, runtime reproduction, numerical validation and untested scope. Preserve failures and unsupported paths in the report.
  • Run relevant format/lint/type/diff checks and disclose unavailable checks. Recheck affected snapshots for concurrent edits before claiming findings are current.

This skill owns shared mechanics only. Patch headers/audits, attention index semantics, registry quantization rules, model structure alignment and model-specific upstream-bug handling stay in their specialist skills. Reusing common checks does not import one specialist's policy into another. No separate audit artifact is required by this skill.

© MetaX-MACA, 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

Files

SKILL.md and 2 other files (scripts, references) in .codex/skills/vllm-metax-upgrade-common of MetaX-MACA/vLLM-metax.

  • SKILL.md
  • references/environment-preflight.md
  • scripts/probe_environment.py

Open the folder on GitHubat commit df0f52b

Compare with similar skills

Vllm Metax Upgrade Common 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.

Vllm Metax Upgrade Common compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vllm Metax Upgrade Common this skillMetaX-MACA/vLLM-metax180—~1.1kAutomated safety check: PassApache-2.0
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Model Evalshuggingface/skills11k2 repos~1.6kAutomated safety check: PassApache-2.0
CI Fails Buildkiteguqiong96/Lvllm4652 repos~349Automated safety check: PassApache-2.0
Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel1.3k—~1.1kAutomated safety check: PassCustom licence
Add Diffusion Modelvllm-project/vllm-omni7.1k—~7kAutomated safety check: PassApache-2.0

Similar skills

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Model Evals

    huggingface/skills

    Official

    Runs evaluations of Hugging Face Hub models on local hardware with inspect-ai or lighteval, and helps choose between vLLM, Transformers and accelerate backends.

    11k GitHub starsUsed in 2 repos~1.6k tokens
    AI & LLM EngineeringAuto-check passed

  • CI Fails Buildkite

    guqiong96/Lvllm

    Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

    465 GitHub starsUsed in 2 repos~349 tokens
    AI & LLM EngineeringAuto-check passed

  • Gptqmodel Tokenizer Normalization

    ModelCloud/GPTQModel

    Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.

    1.3k GitHub stars~1.1k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Add Diffusion Model

    vllm-project/vllm-omni

    Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including native non-Diffusers ports, reference-parity validation, Cache-DiT…

    7.1k GitHub stars~7k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Add Recipe

    vllm-project/vllm-omni

    Add or update an in-repository vLLM-Omni model recipe with verified task, input, output, hardware, command, feature, and validation contracts.

    7.1k GitHub stars~1.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

More from MetaX-MACA/vLLM-metax

  • Vllm Metax Model Upgrade

    MetaX-MACA/vLLM-metax

    Review and upgrade MetaX model support against a target vLLM revision and installed MACA components, recursively including model-dependent attention and kernels.

    180 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • Vllm Metax Registry Upgrade

    MetaX-MACA/vLLM-metax

    Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

    180 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Vllm Metax Attention Upgrade

    MetaX-MACA/vLLM-metax

    Review and adapt MetaX attention backends, MLA, sparse indexers, cache layouts, and their kernel wrappers against a target vLLM revision and the actually installed MetaX component APIs.

    180 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

  • Vllm Metax Patch Upgrade

    MetaX-MACA/vLLM-metax

    Audit and adapt monkey patches in vllmmetax/patch/ against a target upstream revision.

    180 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed

  • Vllm Metax Model Trim

    MetaX-MACA/vLLM-metax

    Trim large MetaX model directories for dummy smoke tests or real-checkpoint loading on limited GPUs.

    180 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Vllm Metax Upgrade Common

What does Vllm Metax Upgrade Common do?

Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades. Vllm Metax Upgrade Common is an agent skill from MetaX-MACA/vLLM-metax. Establish the shared environment, source/runtime correspondence, target confirmation and validation evidence for MetaX vLLM upgrades.

When should I use Vllm Metax Upgrade Common?

Vllm Metax Upgrade Common fits situations like: tasks that involve LLM inference and serving.

How do I install Vllm Metax Upgrade Common in Claude Code?

Run `npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-upgrade-common -a claude-code`. Or copy the skill folder (.codex/skills/vllm-metax-upgrade-common in MetaX-MACA/vLLM-metax) into .claude/skills/vllm-metax-upgrade-common in your project. Claude Code loads it when a task matches its description.

How do I install Vllm Metax Upgrade Common in Codex?

Run `npx skills add MetaX-MACA/vLLM-metax --skill vllm-metax-upgrade-common -a codex`. Or copy the skill folder (.codex/skills/vllm-metax-upgrade-common in MetaX-MACA/vLLM-metax) into .agents/skills/vllm-metax-upgrade-common in your project. Codex loads it when a task matches its description.

Can I use Vllm Metax Upgrade Common 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 MetaX-MACA/vLLM-metax --skill vllm-metax-upgrade-common -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-metax-upgrade-common, .gemini/skills/vllm-metax-upgrade-common, .github/skills/vllm-metax-upgrade-common and .opencode/skills/vllm-metax-upgrade-common in your project.

What does Vllm Metax Upgrade Common need to run?

Going by SKILL.md and its folder, Vllm Metax Upgrade Common needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Vllm Metax Upgrade Common 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 Vllm Metax Upgrade Common 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Vllm Metax Upgrade Common use?

Vllm Metax Upgrade Common 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 Vllm Metax Upgrade Common use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.4k tokens, read only when the agent opens those files.

What are the alternatives to Vllm Metax Upgrade Common?

Skills that share tags, products or a category with Vllm Metax Upgrade Common: SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Model Evals (huggingface/skills, 11k stars), CI Fails Buildkite (guqiong96/Lvllm, 465 stars) and Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vllm Metax Upgrade Common?

MetaX-MACA (a GitHub organization) maintains it in MetaX-MACA/vLLM-metax, which has 180 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.

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