Skip to content
Skill

Physical AI defect image generation

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, met

Install
Scripts
shell, Python
Platforms
Claude Code, Codex, Cursor
GitHub stars
4K
Last commit
1 day ago
License
Apache-2.0
Listing updated
today

When your agent uses it

Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and glass inspection. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint, cosmos defect generation, cosmos-predict2 defect, cosmos-anomalygen, cosmos predict2 finetune.

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 54 files (484 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Install

Copy the skill folder to ~/.claude/skills/physical-ai-defect-image-generation to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/physical-ai-defect-image-generation &&
cp -R "$tmp/skills/physical-ai-defect-image-generation" ~/.claude/skills/physical-ai-defect-image-generation &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/physical-ai-defect-image-generation inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/physical-ai-defect-image-generation to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/physical-ai-defect-image-generation &&
cp -R "$tmp/skills/physical-ai-defect-image-generation" ~/.agents/skills/physical-ai-defect-image-generation &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/physical-ai-defect-image-generation inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/physical-ai-defect-image-generation to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/physical-ai-defect-image-generation &&
cp -R "$tmp/skills/physical-ai-defect-image-generation" ~/.cursor/skills/physical-ai-defect-image-generation &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/physical-ai-defect-image-generation inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/NVIDIA/skills.git --path skills/physical-ai-defect-image-generation

Or copy the folder to ~/.gemini/skills/physical-ai-defect-image-generation yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/physical-ai-defect-image-generation:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/physical-ai-defect-image-generation &&
cp -R "$tmp/skills/physical-ai-defect-image-generation" ~/.copilot/skills/physical-ai-defect-image-generation &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/physical-ai-defect-image-generation inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/NVIDIA/skills.git

Then copy skills/skills/physical-ai-defect-image-generation into your agent's skills folder as physical-ai-defect-image-generation. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

Physical AI defect image generation FAQ

How do I install Physical AI defect image generation in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/physical-ai-defect-image-generation to use it in all your projects, or to .claude/skills/physical-ai-defect-image-generation in one project.

Does Physical AI defect image generation run scripts?

Yes. It runs shell and Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use Physical AI defect image generation?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

What are the best alternatives to Physical AI defect image generation?

The closest alternatives to Physical AI defect image generation are Rea tool design, Codebase design, Frontend design, Canvas design and Web design reviewer.

More from NVIDIA/skills

  1. Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill

    • Open source
    • 4K GitHub stars
  2. Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, null

    • Open source
    • 4K GitHub stars
  3. Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API

    • Open source
    • 4K GitHub stars
  4. Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API

    • Open source
    • 4K GitHub stars
    • Design and media
  5. Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose

    • Open source
    • 4K GitHub stars

Alternatives to Physical AI defect image generation

  1. Audit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.

    • Open source
    • 465K GitHub stars
    • Design and media
  2. Shared vocabulary for designing deep modules

    • Open source
    • 326K GitHub stars
    • Design and media
  3. Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one

    • 196K GitHub stars
    • Design and media
  4. Create beautiful visual art in .png and .pdf documents using design philosophy

    • 196K GitHub stars
    • Design and media
  5. This skill enables visual inspection of websites running locally or remotely to identify and fix design issues

    • Open source
    • 41.3K GitHub stars
    • Design and media
  6. Generate or edit images via OpenRouter with the Gemini 3 Pro Image model

    • Open source
    • 41.3K GitHub stars
    • Design and media