Individual skill
tao-run-dinov3-ssl-deft
Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for active-learning-style DINOv3 mining, not plain pretraining/fine-tuning (tao-train-dinov3) or AOI/PAS DEFT.
skills/tao-run-dinov3-ssl-deft/SKILL.md
Source commit 25340619336e89bcc40365c28bfe9e790430468e
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 3,897
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- claude-code Repository topic
- codex Repository topic
- coding-agents Repository topic
- cuda Repository topic
- developer-tools Repository topic
- llm Repository topic
- omniverse Repository topic
- application Declared skill tag
- workflow Declared skill tag
- deft Declared skill tag
- dinov3 Declared skill tag
- ssl Declared skill tag
- operations Derived category
- data Derived category
- education Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
BENCHMARK.mddoc · 8,173 bytesSKILL.mdcore · 7,508 bytesSKILL.mdcore · 7,508 bytesSKILL.mdcore · 7,508 bytesconfig/skillspector-baseline.yamlasset · 1,419 bytesevals/evals.jsonasset · 4,678 bytesreferences/adapter-contracts.mddoc · 27,550 bytesreferences/architecture.mddoc · 6,981 bytesreferences/metrics.schema.jsonasset · 1,039 bytesreferences/skill_info.yamlasset · 2,021 bytesreferences/stage-request.schema.jsonasset · 3,232 bytesreferences/tao-container-integration.mddoc · 8,318 bytesreferences/workflow.schema.jsonasset · 9,943 bytesskill-card.mddoc · 5,357 bytesskill.oms.sigasset · 6,565 bytes
Read excerpt
# DINOv3 SSL DEFT
The DS-packaged Python controller owns the loop and durable state. This skill
prepares and approves its inputs; it does not implement orchestration.
## Instructions
1. Resolve the DINOv3 model using the model resolver. Choose `grit-score`
for unlabeled target ranking; its scorer is built in. Offer
`multi-task-round-robin` only when the user already has a score adapter
that meets the [task scoring contract](references/adapter-contracts.md#task-scoring):
DS ships no multi-task scorer, and `validate` rejects the recipe's
placeholder. Read [architecture.md](references/architecture.md) for the