fcakyon/labrat · plugin/skills/compare/SKILL.md · Same-epoch comparison and analysis of training runs across wandb, neptune, tensorboard, mlflow, or local result files…
fcakyon/labrat · plugin/skills/dataset-curation/SKILL.md · Use when the user wants to analyze dataset bias, create stratified samples, evaluate fairness, or plan dataset…
fcakyon/labrat · plugin/skills/debug/SKILL.md · Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list…
fcakyon/labrat · plugin/skills/experiment-design/SKILL.md · Use when the user wants to design experiments, plan ablation studies, structure baselines, or create incremental…
fcakyon/labrat · plugin/skills/launch/SKILL.md · Pre-flight checklist for long-running ML training jobs covering config diff, run naming, path verification, monitoring…
fcakyon/labrat · plugin/skills/literature-research/SKILL.md · Use when the user wants to find related work, survey a research area, run a literature gap analysis, or discover…
fcakyon/labrat · plugin/skills/paper-check/SKILL.md · Check a paper against its code, results and citations before submission (numbers, terms, code vs paper, formulas vs…
fcakyon/labrat · plugin/skills/paper-write/SKILL.md · Write, structure, or revise academic paper sections, keep notation consistent, refine figures and tables, and set up or…
fcakyon/labrat · plugin/skills/rebuttal/SKILL.md · Prepare a paper for peer review. Reads the paper and experiment results, selects the strongest ablations, anticipates…
fcakyon/labrat · plugin/skills/reproduce/SKILL.md · End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial…