cdf-curation-and-retrieval — Claude Code skill: setup and installation
The cdf-curation-and-retrieval skill guides video and image curation with Cosmos Curator, plus handoffs to TAO and searches through Cosmos Dataset Search. Use it for requests involving CDF or its Make and CLI workflows.
no license ★ 4,106 updated 2026-10-23
npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a claude-codeWhat cdf-curation-and-retrieval does
The skill helps shape video collections by splitting clips, filtering material, removing duplicates, and preparing shards. For images, its workflow covers annotation and embeddings. Curator outputs can feed later data mining in TAO, while Cosmos Dataset Search has its own ingest and search route.
Before producing pipeline YAML, the agent checks for KPI results, sample data, or a calibration interview. An explicit run also requires config validation and user authorization. The setup calls for a GPU host with NVIDIA drivers and nvidia-container-toolkit, Docker, and access to the Makefile and the configs/, cookbook/, and references/ trees. Without that GPU setup, a pipeline run cannot proceed. Workplace monitoring of employee conduct requires legal review.
What it helps with
- split video into clips and remove duplicates
- filter video collections and divide them into shards
- prepare annotated images with embeddings
- validate Curator output before handing it to TAO
- ingest datasets into Cosmos Dataset Search and search them
Example prompts for the agent
- Set up a Cosmos Curator video pipeline that splits clips and removes duplicates.
- Check what context is needed before writing YAML for an image pipeline.
- Validate the Curator output and prepare it for a TAO handoff.
How to install cdf-curation-and-retrieval
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a claude-code2Manually: put the files in place
~/.claude/skills/cdf-curation-and-retrieval/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cdf-curation-and-retrieval/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a codex2Manually: put the files in place
.agents/skills/cdf-curation-and-retrieval/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a cursor2Manually: put the files in place
.cursor/skills/cdf-curation-and-retrieval/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NVIDIA/skills skills/cdf-curation-and-retrieval2Manually: put the files in place
.github/skills/cdf-curation-and-retrieval/SKILL.md1Skills CLI (Vercel)
npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a gemini-cli2Platform CLI
gemini skills install https://github.com/NVIDIA/skills --path skills/cdf-curation-and-retrievalManually: put the files in place
.devin/skills/cdf-curation-and-retrieval/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.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 cdf-curation-and-retrieval
How do I install cdf-curation-and-retrieval in Claude Code?
Run npx skills add NVIDIA/skills --skill cdf-curation-and-retrieval -a claude-code. The skill file is at ~/.claude/skills/cdf-curation-and-retrieval/SKILL.md.
What does cdf-curation-and-retrieval do?
It guides Cosmos Curator workflows for video and image collections, and supports handoffs to TAO and dataset search through Cosmos Dataset Search.
What must be in place before writing pipeline YAML?
The agent needs KPI output, sample data to inspect, or a calibration interview. If required paths, intent, or hardware constraints remain unresolved, it should stop instead of writing the config.