physical-ai-defect-image-generation — Claude Code skill
Prepares automated defect synthesis pipelines for optical quality inspection. Helps construct training sets for electronic boards, metal, and glass using Cosmos vision models.
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a claude-codeWhat physical-ai-defect-image-generation does
The skill automates the configuration of inspection workflows dispatched through OSMO. At its core is Cosmos AnomalyGen, an adaptation of the Cosmos-Predict2-2B architecture trained for electronic boards, glass surfaces, and raw metal. It provides two primary execution paths: initial cold-start batches derived from USD CAD assets in Day 0, and alignment or manual masking of genuine photographs in Day 1.
Each process runs autonomously through prepared YAML blueprints and cookbook configurations. When testing assembly faults, structural shifts rely on IsaacSim geometry adjustments. In contrast, surface flaws like scratches or omitted components are handled by pairing AnomalyGen with Qwen Image-Edit transformations.
Day 0 routines will fail immediately unless an active image_edit_endpoint is reachable, hosting the appearance transfer model. In addition, generation volume requires configuring two separate thresholds. The render_patches option sets limits on raw scan patches, while crop_max_emit controls the count of exported cell crops.
What it helps with
- synthesize solder bridges and scratches on circuit boards
- simulate missing components and misaligned parts from CAD models
- register authentic board photography against reference CAD definitions
- produce defect image collections for metal and glass inspection
- execute non-interactive AnomalyGen finetuning jobs via OSMO
Example prompts for the agent
- Draft an OSMO configuration for Day 0 defect synthesis using our PCBA USD scene
- Set up a Day 1 alignment job to register raw circuit board photos
- Create an OSMO workflow to fine-tune AnomalyGen on metal surface anomalies
How to install physical-ai-defect-image-generation
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a claude-code2Manually: put the files in place
~/.claude/skills/physical-ai-defect-image-generation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/physical-ai-defect-image-generation/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a codex2Manually: put the files in place
.agents/skills/physical-ai-defect-image-generation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a cursor2Manually: put the files in place
.cursor/skills/physical-ai-defect-image-generation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills physical-ai-defect-image-generation2Manually: put the files in place
.github/skills/physical-ai-defect-image-generation/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/physical-ai-defect-image-generationManually: put the files in place
.devin/skills/physical-ai-defect-image-generation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about physical-ai-defect-image-generation
How do I install physical-ai-defect-image-generation in Claude Code?
Run npx skills add NVIDIA/skills --skill physical-ai-defect-image-generation -a claude-code. This downloads the skill to ~/.claude/skills/physical-ai-defect-image-generation/SKILL.md.
What does physical-ai-defect-image-generation do?
It coordinates defect creation pipelines on OSMO for visual quality inspection. The tool automates dataset generation and model fine-tuning across circuit boards, glass, and metal surfaces.
What external service must be running for Day 0 pipelines?
Day 0 executions depend on an accessible image_edit_endpoint hosting Qwen Image-Edit. Without that endpoint active, image augmentation cannot process the rendered scan patches.
