FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
DINOv3 self-supervised DEFT loop on unlabeled pools v1.0.0
Use this resource to iteratively select and retrain DINOv3 data from an unlabeled pool
New
- 456 downloads
- 231 likes
- 126 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install dinov3-active-learning-selectionWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent resolves the DINOv3 model, picks the GRIT score to rank unlabeled targets, then prepares and gets approval for the loop inputs. It does not implement the orchestration: the Python controller runs the loop and durable state.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md: method, approval and monitoring
- references/architecture.md: loop architecture
- references/adapter-contracts.md: score adapter contracts
Good fit for
- You have many unlabeled images and want to pick which ones to annotate
- You want active learning with DINOv3 rather than plain fine-tuning
Not for
Tags
- dinov3
- active learning
- unlabeled
- tao
About
You say
“Select the most useful images from my unlabeled pool with DINOv3 and the GRIT score.”
Skill published by nvidia under the Apache-2.0 license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to iteratively select and retrain DINOv3 data from an unlabeled pool
- Review and adjust the result
Content preview
Files
- BENCHMARK.md8.1 KB
- config/skillspector-baseline.yaml1.4 KB
- evals/evals.json4.6 KB
- LICENSE11.3 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/adapter-contracts.md27.4 KB
- references/architecture.md6.9 KB
- references/metrics.schema.json1 KB
- references/skill_info.yaml2 KB
- references/stage-request.schema.json3.2 KB
- references/tao-container-integration.md8.3 KB
- references/workflow.schema.json10 KB
- skill-card.md5.3 KB
- SKILL.md7.5 KB
- skill.oms.sig6.4 KB
Origin and licence
Listed unmodified
- Author
- nvidia
- Source
- github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-run-dinov3-ssl-deft
- Licence
- Apache-2.0
Notice
« tao-run-dinov3-ssl-deft » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…