Menu
Analyze YOLO training runs — compares to baseline/best, checks per-class regression, analyzes training dynamics and tune convergence, writes actionable recommendations.
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 — creates cron jobs to track long-running training, auto-continue pipeline when training completes.
Audit YOLO dataset quality — 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.
Run autonomous YOLO training experiments — 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.
Initialize a new YOLO project — detects your dataset's starting state and routes through the right tools.
| name | analyze-results |
| description | Analyze YOLO training runs — compares to baseline/best, checks per-class regression, analyzes training dynamics and tune convergence, writes actionable recommendations. |
Single-pass analysis run after each experiment or on-demand via /analyze.
Read:
results.csv or tune_results.csvexperiments/summary.md journal entriesexperiments/dataset_profile.yamltraining-plan.md (thresholds, goals, constraints)experiments/exp_NNN_name/train/results.csvexperiments/exp_NNN_name/results.csvmetrics.yaml — note that training dynamics analysis is unavailableFor tune runs, also check:
experiments/exp_NNN_name/tune/tune_results.csvComparison: Latest vs baseline AND current best (mAP50-95, per-class AP)
Per-class regression check: Flag any class exceeding training-plan.md threshold vs current best
Training dynamics (if results.csv available):
Tune analysis (if tune_results.csv available):
Diminishing returns detection (when 3+ experiments show <0.5% change):
Recommendations: Ordered by expected impact. Each cites evidence from the analysis.
Write experiments/analysis.md with findings and recommendations. Print top 3 findings + top 3 recommendations.
Findings also inform the journal entry's learning field and the next DIAGNOSE step in the reasoning loop.
analysis.md from the previous experiment or last explicit /analyze. It does NOT read analysis of the experiment that just ran before it has been analyzed.