Install Miles Diffusion
radixark/miles_diffusion
Fallback installer for milesdiffusion on a bare CUDA 12.9 Linux GPU box, reproducing the official radixark/milesdiffusion image's package versions and verifying them.
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification.
Install Cosmos3 Setup
$ npx skills add NVIDIA/cosmos-framework --skill cosmos3-setup -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-setup --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-setup .claude/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .claude/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setupType 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-setup -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-setup --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-setup .agents/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .agents/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setup -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-setup --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-setup .cursor/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .cursor/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setup--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-setup -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install NVIDIA/cosmos-framework cosmos3-setup --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-setup .gemini/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .gemini/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setupInstalls 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-setup -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-setup .github/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .github/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setup -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-setup --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-setup .opencode/skills/cosmos3-setup && 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-setup" agent skill from https://github.com/NVIDIA/cosmos-framework/tree/main/.agents/skills/cosmos3-setup into .opencode/skills/cosmos3-setup/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cosmos3-setup", 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-setup- GitHub stars
- 556
- Token cost
- ~1.1k tokens
- SKILL.md length
- 392 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification.
- Works in 6 steps: Clone the repository and cd into the… → System deps: sudo apt-get install -y… → Install uv: curl -LsSf… → …
- The user asks how do I install cosmos3
- SKILL.md covers When to use this skill, Path convention, Where to find answers and Setup steps at a glance, plus 2 more sections
- Calls uv, apt-get and curl; reaches astral.sh; needs HF_TOKEN and HUGGING_FACE_HUB_TOKEN
What it does
Cosmos3 Setup is an agent skill from NVIDIA/cosmos-framework, published by the product's own GitHub organization. Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification. Use when the user asks "how do I install cosmos3", "how do I set up the environment", "how do I download checkpoints", "how do I use Docker", or any question about getting the package running for the first time.
Its SKILL.md is about 1.1k 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 DevOps & Cloud, covering Containers. It works with Docker and CUDA. 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 install cosmos3
- How do I set up the environment
- How do I download checkpoints
- How do I use Docker
Example prompts
- “how do I install cosmos3”
- “how do I set up the environment”
- “how do I download checkpoints”
- “/cosmos3-setup”
Requirements
- Python 3
- Docker
- A credential in HUGGING_FACE_HUB_TOKEN
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Clone the repository and cd into the project root (the directory containing pyproject.toml)
- System deps: sudo apt-get install -y --no-install-recommends curl ffmpeg git-lfs libx11-dev tree wget
- Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh && source $HOME/.local/bin/env
- Install package: uv sync --all-extras --group=cu130-train && source .venv/bin/activate && export LD_LIBRARY_PATH= (use cu128-train on…
- Checkpoints: auto-downloaded during inference; requires HuggingFace auth (see docs)
- Verify: uv run --all-extras --group=cu130-train python -c "import cosmos_framework; print('ok')"
What it can do on your machine
Read from SKILL.md and the folder at commit cf5d68c. 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:
uvapt-getcurlsh
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
astral.sh
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
HF_TOKENHUGGING_FACE_HUB_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Cosmos3 Setup loads about 1.1k tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 392 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteRuns commands with sudoSKILL.md:42
2. **System deps**: `sudo apt-get install -y --no-install-recommends curl ffmpeg git-lfs libx11-dev tree wget` - NotePipes a well-known installer script into a shellSKILL.md:43
3. **Install uv**: `curl -LsSf https://astral.sh/uv/install.sh | sh && source $HOME/.local/bin/env`
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 392 words (~1,082 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-setup
Files
Just SKILL.md in .agents/skills/cosmos3-setup of NVIDIA/cosmos-framework.
Open the folder on GitHubat commit cf5d68c
Compare with similar skills
Cosmos3 Setup 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 Setup this skillNVIDIA/cosmos-framework | 556 | — | ~1.1k | Automated safety check: Notes | Custom licence | |
| Install Miles Diffusionradixark/miles_diffusion | 107 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Init GPU Serverdrawthingsai/draw-things-community | 579 | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Kermt SetupNVIDIA/skills | 3.5k | 1 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Tao Setup Nvidia GPU HostNVIDIA/skills | 3.5k | — | ~3.4k | Automated safety check: Notes | Apache-2.0 | |
| Holoscan Install ContainerNVIDIA/skills | 3.5k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Init GPU Server
drawthingsai/draw-things-community
Initialize a Draw Things GPU server with GPUScript, including script sync, Docker/CUDA/NVIDIA runtime setup, 7T data disk mounting, mergerfs, and end-to-end GPU verification.
- Official
Kermt Setup
NVIDIA/skills
Bootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test…
- Official
Tao Setup Nvidia GPU Host
NVIDIA/skills
Host setup for TAO GPU backends. An agent skill from NVIDIA/skills.
- Official
Holoscan Install Container
NVIDIA/skills
Install Holoscan SDK via the NGC Docker container. An agent skill from NVIDIA/skills.
- Official
Cuopt Install
NVIDIA/skills
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install.
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 Inference
NVIDIA/cosmos-framework
Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling parameters, and prompt upsampling.
- 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…
Related
Categories
Questions about Cosmos3 Setup
What does Cosmos3 Setup do?
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification. Cosmos3 Setup is an agent skill from NVIDIA/cosmos-framework, published by the product's own GitHub organization. Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification.
When should I use Cosmos3 Setup?
Cosmos3 Setup fits situations like: the user asks how do I install cosmos3; how do I set up the environment; how do I download checkpoints; how do I use Docker.
How do I install Cosmos3 Setup in Claude Code?
Run `npx skills add NVIDIA/cosmos-framework --skill cosmos3-setup -a claude-code`. Or copy the skill folder (.agents/skills/cosmos3-setup in NVIDIA/cosmos-framework) into .claude/skills/cosmos3-setup in your project. Claude Code loads it when a task matches its description.
How do I install Cosmos3 Setup in Codex?
Run `npx skills add NVIDIA/cosmos-framework --skill cosmos3-setup -a codex`. Or copy the skill folder (.agents/skills/cosmos3-setup in NVIDIA/cosmos-framework) into .agents/skills/cosmos3-setup in your project. Codex loads it when a task matches its description.
Can I use Cosmos3 Setup 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-setup -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-setup, .gemini/skills/cosmos3-setup, .github/skills/cosmos3-setup and .opencode/skills/cosmos3-setup in your project.
What does Cosmos3 Setup need to run?
Going by SKILL.md and its folder, Cosmos3 Setup needs the command-line tools its instructions call (uv, apt-get, curl and sh) and credentials named HF_TOKEN and HUGGING_FACE_HUB_TOKEN. Our summary lists: Python 3; Docker; A credential in HUGGING_FACE_HUB_TOKEN.
Does Cosmos3 Setup access the network?
SKILL.md names 1 domain. In commands or code: astral.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Cosmos3 Setup safe to install?
Our automated static check of SKILL.md found notes only (runs commands with sudo; pipes a well-known installer script into a shell), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Cosmos3 Setup use?
Cosmos3 Setup 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 Setup use?
About 1.1k tokens (SKILL.md is roughly 4.3k 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 Setup?
Skills that share tags, products or a category with Cosmos3 Setup: Install Miles Diffusion (radixark/miles_diffusion, 107 stars), Init GPU Server (drawthingsai/draw-things-community, 579 stars), Kermt Setup (NVIDIA/skills, 3.5k stars) and Tao Setup Nvidia GPU Host (NVIDIA/skills, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cosmos3 Setup?
NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/cosmos-framework, which has 556 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 26, 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.