Menu
Pull human-corrected annotations from CVAT into local YOLO dataset for training.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Set up autonomous training monitoring โ creates cron jobs to track long-running training, auto-continue pipeline when training completes.
Audit YOLO dataset quality โ class distribution, annotation quality, image stats, and improvement suggestions.
Orchestrate the full active learning loop: train, analyze, push to CVAT, wait for review, pull, merge, retrain.
Analyze YOLO training runs โ compares to baseline/best, checks per-class regression, analyzes training dynamics and tune convergence, writes actionable recommendations.
Run autonomous YOLO training experiments โ reads training-plan.md, assesses bottlenecks, acts strategically, and delegates HP optimization to model.tune().
Profile YOLO model inference speed, FPS, and size across image sizes and export formats.
| name | cvat-pull |
| description | Pull human-corrected annotations from CVAT into local YOLO dataset for training. |
Pull human-corrected annotations from CVAT into your local dataset.
yolo-project.yaml has cvat: section with url and project_idCVAT_ACCESS_TOKEN env var is setproject_id from yolo-project.yamlyolo-cvat pull --task <TASK_ID>
# or
yolo-cvat pull --project <PROJECT_ID>
yolo-validate <output_path>
Check for:
If the user already has a local dataset:
yolo-merge --sources <existing_labels> <pulled_labels> --output <merged>
Has existing local dataset?
โโโ Yes โ Compare distributions โ Suggest yolo-merge
โโโ No โ Set as primary dataset
Validation warnings found?
โโโ Yes โ Flag issues, ask before training
โโโ No โ Ready to train
Class distribution changed?
โโโ Significantly โ Warn user, may affect model balance
โโโ Minor โ Proceed normally