physical-ai-defect-image-generation agent skill by NVIDIA
Orchestrates defect image generation with NVIDIA Cosmos AnomalyGen on OSMO for PCBA, metal surface, and glass inspection, including setup, finetuning checkpoints, and deployment configuration.
At a glance
| Publisher | NVIDIA Official |
|---|---|
| Repository | NVIDIA/skills (396 listed skills) |
| Category | Video, Image, Audio and Creative |
| License | CC-BY-4.0 AND Apache-2.0 |
| Last commit | October 17, 2026 (repository) |
| SKILL.md | 184 lines, 2,243 words |
| Bundled files | 54 files, including references, scripts, assets or templates |
| Quality score | 79/100 · C Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the listing badge and raise the score |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: 5 script files (4 Shell, 1 Python). Your agent may run them, so read them first.
- Environment variables its scripts read:
HF_TOKEN. Check SKILL.md for which ones it needs. - Network: its scripts use an HTTP client or a cloud SDK, and name
huggingface.co. - License: CC-BY-4.0 AND Apache-2.0, an open-source or open-content license.
Install physical-ai-defect-image-generation
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/NVIDIA/skills/tree/main/skills/physical-ai-defect-image-generationtmp="$(mktemp -d)"
git clone --depth 1 https://github.com/NVIDIA/skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/physical-ai-defect-image-generation .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo NVIDIA/skills \
--path skills/physical-ai-defect-image-generationNVIDIA/skills is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes 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 description field of SKILL.md. Agents read this line to decide when to load the skill.
Sections in SKILL.md
- Table of Contents
- Supported Flows
- Pick the right workflow for the user's defect class
- User intent → knob mapping
- Structural-defect sizing (no cropmaxemit knob exists)
- Disambiguation: handle vague requests before committing
- Step 0: Select Flow, Cookbook, and Gather Inputs
- First-time gate
- Preflight ordering (after the first-time gate)
- Common Preconditions (all flows)
- Flow walkthroughs
- Cross-flow invariants
- OSMO Monitoring
- Response Template
- Supporting files
Files in the skill folder
BENCHMARK.mdSKILL.mdassets/configs/finetune.yamlassets/configs/good_image_generation.yamlassets/configs/setup/setup_glass.yamlassets/configs/setup/setup_metal.yamlassets/configs/setup/setup_pcb.yamlassets/configs/setup/setup_pretrained.yamlassets/configs/structural_defect_generation.yamlassets/configs/texture_defect_generation_day0.yamlassets/configs/texture_defect_generation_day1_manual_roi.yamlassets/configs/texture_defect_generation_day1_real_alignment.yamlassets/cookbooks/glass/ag_config.yamlassets/cookbooks/metal_surface/ag_config.yamlassets/cookbooks/pcb/0603_H100/day0_crop.yamlassets/cookbooks/pcb/0603_H100/day0_image.yamlassets/cookbooks/pcb/0603_H100/defect_image.yamlassets/cookbooks/pcb/0603_H100/pcba_target.yamlassets/cookbooks/pcb/0603_H100/usd2roi_nvpcb.yamlassets/cookbooks/pcb/1152819000/day0_crop.yamlassets/cookbooks/pcb/1152819000/day0_image.yamlassets/cookbooks/pcb/1152819000/defect_image.yamlassets/cookbooks/pcb/1152819000/pcba_target.yamlassets/cookbooks/pcb/1152819000/usd2roi_nvpcb.yaml
Showing 24 of 54 files. Browse the folder on GitHub.
Suede Skill Check: 79/100 · C
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 4fc9cf6cec78. Report version c209010265c9. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Description length: 1 of 5 points. 5 for 150–600 characters; 3 for 100–900; 1 for 50–1,024.
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
physical-ai-defect-image-generation passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 1 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 3 of 3 |
| Bundled scripts | 2 of 2 |
| Recent maintenance | 9 of 9 |
| Curated-list citations | 1 of 7 |
| Tool permissions declared | 0 of 2 |
| Compatibility declared | 0 of 2 |
Show the listing and raise the score
physical-ai-defect-image-generation is listed with 79/100 · C. This badge links to its Suede listing. Skills scoring 80–99 add a numeric and a letter quality shield; the largest open points for physical-ai-defect-image-generation are boundary clause (4), description length (4) and example request (3). Send your repository and the points you want to raise, then request a fresh review after updating the skill.
[](https://skills.suedeai.ai/directory/nvidia/skills/physical-ai-defect-image-generation/)<a href="https://skills.suedeai.ai/directory/nvidia/skills/physical-ai-defect-image-generation/"><img src="https://skills.suedeai.ai/directory/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Where this skill is cited
NVIDIA/skills appears in 1 curated list: VoltAgent/awesome-agent-skills.