LoRA Space Builder
huggingface/skills
Builds and publishes a Gradio demo on Hugging Face Spaces for a LoRA, with the pipeline, UI and settings chosen to match that LoRA's task and model card.
Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling.
Install Cosmos3 Inference
$ npx skills add NVIDIA/cosmos-framework --skill cosmos3-inference -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-inference --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/NVIDIA/cosmos-framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/cosmos3-inference .claude/skills/cosmos3-inference && 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 "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .claude/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inferenceType 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 NVIDIA/cosmos-framework --skill cosmos3-inference -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-inference --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/cosmos-framework.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/cosmos3-inference .agents/skills/cosmos3-inference && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .agents/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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 NVIDIA/cosmos-framework --skill cosmos3-inference -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-inference --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/cosmos-framework.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/cosmos3-inference .cursor/skills/cosmos3-inference && 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 "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .cursor/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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/NVIDIA/cosmos-framework.git --path .agents/skills/cosmos3-inference--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 NVIDIA/cosmos-framework --skill cosmos3-inference -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-inference --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/cosmos-framework.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/cosmos3-inference .gemini/skills/cosmos3-inference && 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 "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .gemini/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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 NVIDIA/cosmos-framework cosmos3-inferenceInstalls 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 NVIDIA/cosmos-framework --skill cosmos3-inference -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/NVIDIA/cosmos-framework.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/cosmos3-inference .github/skills/cosmos3-inference && 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 "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .github/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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 NVIDIA/cosmos-framework --skill cosmos3-inference -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-inference --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/NVIDIA/cosmos-framework.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/cosmos3-inference .opencode/skills/cosmos3-inference && 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 "cosmos3-inference" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-inference into .opencode/skills/cosmos3-inference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-inference", 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
cosmos3-inference- GitHub stars
- 558
- Token cost
- ~1.2k tokens
- SKILL.md length
- 376 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling.
- The user asks how do I run inference
- SKILL.md covers When to use this skill, Path convention, Where to find answers and Things not obvious from the docs, plus 1 more section
- Calls uv
- How do I generate a video
What it does
Cosmos3 Inference is an agent skill from NVIDIA/cosmos-framework, published by the product's own GitHub organization. Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling. Use when the user asks "how do I run inference", "how do I generate a video", "how do I serve the model", "what parameters should I use", or any question about running the model to produce outputs.
Its SKILL.md is about 1.2k 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 Model hubs and datasets. It works with Gradio. The repository describes itself as: Our inference and training framework to run on the Cosmos Models.
When your agent uses it
- The user asks how do I run inference
- How do I generate a video
- How do I serve the model
- What parameters should I use
Example prompts
- “how do I run inference”
- “how do I generate a video”
- “how do I serve the model”
- “/cosmos3-inference”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 8aca062. 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:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, 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
Cosmos3 Inference loads about 1.2k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 376 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.
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 376 words (~1,212 tokens).
“All paths below are relative to the cosmos3 package root (../../../ from this skill file). All uv run / python commands should also be run from there.”
- name
- cosmos3-inference
Files
Just SKILL.md in .agents/skills/cosmos3-inference of NVIDIA/cosmos-framework.
Open the folder on GitHubat commit 8aca062
Compare with similar skills
Cosmos3 Inference 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 |
|---|---|---|---|---|---|---|
| Cosmos3 Inference this skillNVIDIA/cosmos-framework | 558 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| LoRA Space Builderhuggingface/skills | 11k | 2 repos | ~8.4k | Automated safety check: Pass | Apache-2.0 | |
| Space Doctorhuggingface/hf-mcp-server | 302 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Generate Openenv Envadithya-s-k/FineEnvs | 443 | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face ZeroGPUhuggingface/skills | 11k | 2 repos | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Huggingface Spaceshuggingface/skills | 11k | 1 repos | ~4.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
- Official
Space Doctor
huggingface/hf-mcp-server
Diagnose broken Hugging Face Gradio Spaces from their actual logs and pinned source, then prepare a minimal verified source fix as candidate files.
Generate Openenv Env
adithya-s-k/FineEnvs
Builds an OpenEnv (Hugging Face) variant of an RL environment.
- Official
Hugging Face ZeroGPU
huggingface/skills
Covers the rules for writing Gradio Spaces on ZeroGPU hardware: the @spaces.GPU decorator, duration and quota tuning, process isolation and CUDA build limits.
- Official
Huggingface Spaces
huggingface/skills
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community…
- Official
Hf MCP
huggingface/skills
Use Hugging Face Hub via MCP server tools. An agent skill from huggingface/skills.
More from NVIDIA/cosmos-framework
- Official
Cosmos3 Codebase Nav
NVIDIA/cosmos-framework
Navigate the Cosmos3 package codebase to find where parameters, configs, defaults, scripts, and documentation live.
- Official
Cosmos3 Env Troubleshoot
NVIDIA/cosmos-framework
Diagnose and fix Cosmos3 environment, installation, and runtime errors.
- Official
Cosmos3 Post Training
NVIDIA/cosmos-framework
Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired…
- Official
Cosmos3 Setup
NVIDIA/cosmos-framework
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification.
Related
Works with
Categories
Questions about Cosmos3 Inference
What does Cosmos3 Inference do?
Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling. Cosmos3 Inference is an agent skill from NVIDIA/cosmos-framework, published by the product's own GitHub organization. Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling.
When should I use Cosmos3 Inference?
Cosmos3 Inference fits situations like: the user asks how do I run inference; how do I generate a video; how do I serve the model; what parameters should I use.
How do I install Cosmos3 Inference in Claude Code?
Run `npx skills add NVIDIA/cosmos-framework --skill cosmos3-inference -a claude-code`. Or copy the skill folder (.agents/skills/cosmos3-inference in NVIDIA/cosmos-framework) into .claude/skills/cosmos3-inference in your project. Claude Code loads it when a task matches its description.
How do I install Cosmos3 Inference in Codex?
Run `npx skills add NVIDIA/cosmos-framework --skill cosmos3-inference -a codex`. Or copy the skill folder (.agents/skills/cosmos3-inference in NVIDIA/cosmos-framework) into .agents/skills/cosmos3-inference in your project. Codex loads it when a task matches its description.
Can I use Cosmos3 Inference 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 NVIDIA/cosmos-framework --skill cosmos3-inference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cosmos3-inference, .gemini/skills/cosmos3-inference, .github/skills/cosmos3-inference and .opencode/skills/cosmos3-inference in your project.
What does Cosmos3 Inference need to run?
Going by SKILL.md and its folder, Cosmos3 Inference needs the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Cosmos3 Inference access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Cosmos3 Inference 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 Cosmos3 Inference use?
Cosmos3 Inference 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 Cosmos3 Inference use?
About 1.2k tokens (SKILL.md is roughly 4.8k 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 Cosmos3 Inference?
Skills that share tags, products or a category with Cosmos3 Inference: LoRA Space Builder (huggingface/skills, 11k stars), Space Doctor (huggingface/hf-mcp-server, 302 stars), Generate Openenv Env (adithya-s-k/FineEnvs, 443 stars) and Hugging Face ZeroGPU (huggingface/skills, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cosmos3 Inference?
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/cosmos-framework, which has 558 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: NVIDIA/cosmos-framework on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.