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

Add Recipe

by vllm-project in 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.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Add Recipe

skills CLI
$ npx skills add vllm-project/vllm-omni --skill add-recipe -a claude-code

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

GitHub CLI
$ gh skill install vllm-project/vllm-omni add-recipe --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/vllm-project/vllm-omni.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/add-recipe .claude/skills/add-recipe && 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
add-recipe
GitHub stars
7.1k
Token cost
~1.4k tokens
SKILL.md length
613 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
Apache-2.0

At a glance

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

  • Works in 9 steps: Summary: vendor, exact model ID,… → Supported model contract: put task,… → References: link the canonical model… → …
  • Creating files under recipes/
  • SKILL.md covers Source the contract, Route by model family, Structure the recipe and Separate hardware from software, plus 4 more sections
  • Calls git

What it does

Add Recipe is an agent skill from 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. Use when creating files under recipes/, restructuring a recipe after review, documenting a newly supported model, or synchronizing recipe claims with support tables and shared feature guides.

Its SKILL.md is about 1.4k 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. It works with vLLM. The repository describes itself as: A framework for efficient model inference with omni-modality models. The licence is Apache-2.0.

When your agent uses it

  • Creating files under recipes/
  • Restructuring a recipe after review
  • Documenting a newly supported model
  • Synchronizing recipe claims with support tables and shared feature guides

Example prompts

  • “/add-recipe”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Summary: vendor, exact model ID, runtime, modes, named hardware,
  2. Supported model contract: put task, input, output, and provided-profile
  3. References: link the canonical model source, shared examples, supported
  4. Checkpoint/setup: pin revisions when possible and state required assets.
  5. Hardware: document the single accelerator named by the file suffix,
  6. Commands: reuse shared examples/ entrypoints unless the model contract
  7. Supported features: use a compact model-specific topology/status table
  8. Verification: provide a quick command and exact expected output
  9. Qualification evidence: report correctness, memory, and timing evidence

What it can do on your machine

Read from SKILL.md and the folder at commit e4af781. 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:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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

Add Recipe loads about 1.4k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 613 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~86
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 vllm-project/vllm-omni at commit e4af781, republished under its Apache-2.0 licence (© vllm-project). 613 words, ~1,433 tokens.

Download SKILL.mdSave it as .claude/skills/add-recipe/SKILL.md (or your agent's skills folder).
name
add-recipe
description
Add or update an in-repository vLLM-Omni model recipe with verified task, input, output, hardware, command, feature, and validation contracts. Use when creating files under recipes/, restructuring a recipe after review, documenting a newly supported model, or synchronizing recipe claims with support tables and shared feature guides.

Add a vLLM-Omni Recipe

Source the contract

Read recipes/TEMPLATE.md and recipes/README.md before editing. Inspect the canonical model card/repository, implementation, shared examples, tests, and available local qualification evidence.

Do not infer support from a model name, sibling recipe, registry entry, or topology validator. Mark unexecuted configurations as configuration-only.

Route by model family

Read only the contributor and user documentation relevant to the model:

FamilyContributor guideUser-facing documentation to synchronize
Diffusionadding a diffusion modeldocs/user_guide/diffusion_features.md, applicable diffusion feature guides, and shared image/video/audio examples
TTSadding a TTS modelexamples/offline_inference/text_to_speech/README.md, examples/online_serving/text_to_speech/README.md, and docs/serving/speech_api.md
Omniadding an omni modelmodel-family offline/online example docs, docs/serving/chat_completions_api.md, and docs/user_guide/feature_compatibility.md

All families must update docs/models/supported_models.md and the matching row in recipes/README.md. Do not add a modality-specific support document when the repository has no such table; update the closest shared user contract.

Structure the recipe

Keep the recipe task-oriented and use one hardware-specific file named recipes/<vendor>/<model>-<hardware>.md. A recipe may contain multiple deployment topologies on that hardware, but each additional accelerator model or platform requires its own suffixed file.

  1. Summary: vendor, exact model ID, runtime, modes, named hardware, recommended deployment, and maintainer.
  2. Supported model contract: put task, input, output, and provided-profile tables before setup or commands.
  3. References: link the canonical model source, shared examples, supported model table, and feature matrix.
  4. Checkpoint/setup: pin revisions when possible and state required assets.
  5. Hardware: document the single accelerator named by the file suffix, including every validated device-count/topology profile on it.
  6. Commands: reuse shared examples/ entrypoints unless the model contract truly requires a dedicated script. Include offline and online paths that were validated.
  7. Supported features: use a compact model-specific topology/status table with links to shared feature guides.
  8. Verification: provide a quick command and exact expected output contract.
  9. Qualification evidence: report correctness, memory, and timing evidence with its measurement scope and caveats.

Separate hardware from software

For every locally validated hardware profile, record:

  • accelerator vendor/model and per-device memory;
  • number of devices;
  • interconnect (NVLink, PCIe, or the platform equivalent);
  • host memory when CPU staging/offload is material;
  • whether the profile is runtime-qualified or configuration-only.

Record OS, Python, driver/runtime, framework versions, and the vLLM-Omni revision in a separate software-environment table. Keep precision, worker count, and DP/TP/SP/PP sizes with the deployment profile or exact command.

Never generalize a result from one accelerator family to another or combine NVIDIA, AMD, NPU, or distinct accelerator models in one recipe. Create a separate hardware-suffixed recipe and recipes/README.md row. Distinguish upstream requirements from hardware exercised by the PR.

Show full SKILL.md (198 more words)Show less

Keep shared documentation concise

Link the applicable diffusion, TTS, omni, serving, or design guide for generic feature semantics and launch instructions. The recipe should contain only the model-specific status, valid topology, required flag difference, and evidence boundary.

Put unsupported combinations in the same feature table. Avoid repeating the same model-specific prose below the global feature matrix; the recipe is the detailed source of truth.

Report evidence precisely

For every performance or memory value, state:

  • checkpoint/revision and workload;
  • accelerator and device count;
  • precision and topology;
  • cold/warm scope, step count, and concurrency;
  • peak HBM and host-memory metric when measured;
  • output/quality guard and sample count;
  • monitoring overhead or other known variance.

Call a single bounded run qualification evidence, not a benchmark. Do not add a benchmark script unless the contribution explicitly requires one.

Synchronize repository documentation

Update all applicable locations:

  • the row in recipes/README.md;
  • docs/models/supported_models.md;
  • the family-specific documentation selected in Route by model family;
  • shared example documentation when commands or flags change.

Keep global support tables compact. Link to the recipe instead of duplicating its deployment explanation.

Validate

Run, at minimum:

bash
pre-commit run --files <changed recipe/docs/skill files>
mkdocs build --strict
git diff --check

Remove generated documentation artifacts after validation. Confirm every recipe link resolves and every claimed profile has matching code or evidence.

© vllm-project, 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

Just SKILL.md in .claude/skills/add-recipe of vllm-project/vllm-omni.

Open the folder on GitHubat commit e4af781

Compare with similar skills

Add Recipe 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.

Add Recipe compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Add Recipe this skillvllm-project/vllm-omni7.1k—~1.4kAutomated 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
Vllm Metax Model UpgradeMetaX-MACA/vLLM-metax180—~3.2kAutomated 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

  • 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 today
    AI & LLM EngineeringAuto-check passed

  • Triton Kernel Writing

    guqiong96/Lvllm

    Write or review Triton kernels for vLLM, with practical guidance for generated-code inspection, launch grids, indexing, specialization, tuning, and representative performance validation.

    465 GitHub starsUsed in 1 repo~831 tokens
    AI & LLM EngineeringAuto-check passed

More from vllm-project/vllm-omni

All 20 skills in this repo

  • Diffusion Perf Opt

    vllm-project/vllm-omni

    Diagnose and optimize vLLM Omni diffusion workloads, especially Wan/Qwen/Flux-style image and video generation.

    7.1k GitHub stars~7.5k tokensUpdated today
    Auto-check passed

  • Precheck PR

    vllm-project/vllm-omni

    Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.

    7.1k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Quantization

    vllm-project/vllm-omni

    Work on vLLM-Omni quantization for diffusion, autoregressive, omni, or multi-stage models.

    7.1k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Review PR

    vllm-project/vllm-omni

    Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings.

    7.1k GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • H3 Prompt Writing

    vllm-project/vllm-omni

    Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA.

    7.1k GitHub starsUsed in 6 repos~744 tokens
    Auto-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
    Auto-check passed

Works with

Categories

Questions about Add Recipe

What does Add Recipe do?

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

When should I use Add Recipe?

Add Recipe fits situations like: creating files under recipes/; restructuring a recipe after review; documenting a newly supported model; synchronizing recipe claims with support tables and shared feature guides.

How do I install Add Recipe in Claude Code?

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

How do I install Add Recipe in Codex?

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

Can I use Add Recipe 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 vllm-project/vllm-omni --skill add-recipe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/add-recipe, .gemini/skills/add-recipe, .github/skills/add-recipe and .opencode/skills/add-recipe in your project.

What does Add Recipe need to run?

Going by SKILL.md and its folder, Add Recipe needs the command-line tools its instructions call (git).

Does Add Recipe access the network?

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

Is Add Recipe 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 Add Recipe use?

Add Recipe 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 Add Recipe use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Add Recipe?

Skills that share tags, products or a category with Add Recipe: 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 Add Recipe?

vllm-project (a GitHub organization) maintains it in vllm-project/vllm-omni, which has 7,107 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 10, 2026.

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