Menu
O SkillsMP coletou 9 skills de eightmm/oh-my-setting. Abra uma skill para revisar a origem e os detalhes.
Mostrando 9 de 9 skills coletadas.
Shared state, graph-guided work, typed runtime projections, recovery, peer consultation and review, isolated delegation, patch landing, bounded autonomy, experiments, Draft PRs, and cross-provider handoff.
Idioma do texto original: inglês
Resolve implementation-shaping choices for new projects, repo onboarding, unresolved drafts, or broad features. Inspect first and ask only about material gaps; clear bounded changes do not require an interview.
Idioma do texto original: inglês
Register datasets and splits in a manifest and check group leakage and split drift before training: declared group keys (not row identity) decide train/eval separation, so the same protein, patient, or source never sits on both sides.
Idioma do texto original: inglês
Run training and evaluation as registered experiments instead of ad-hoc launches: check the experiment board for duplicates, pre-register hypothesis runs, gate long runs through the run ledger, capture a reproducibility capsule, and record outcomes where the…
Idioma do texto original: inglês
Discipline for launching training or inference on a local GPU machine (not a Slurm cluster): check VRAM and running processes before launching, serialize GPU jobs through the tsp queue instead of racing other work, read the machine snapshot for hardware…
Idioma do texto original: inglês
Work on a Slurm cluster through the private cluster reference and the harness job tools instead of re-probing the cluster every time. Use for sbatch/srun submissions, queue or partition questions, node and GPU availability, job monitoring, and post-job log…
Idioma do texto original: inglês
Maintain an oh-my-setting installation from chat: status, update, doctor, duplicate-skill cleanup, local snapshots, rollback, or uninstall. Use `oms-agent-harness` instead for repository task state.
Idioma do texto original: inglês
Explain why an observed failure or anomaly happened before changing anything: competing hypotheses, ranked evidence, and the cheapest probe that tells them apart. Use for regressions, silent wrong results, flaky or unreproducible behaviour, and "why did this…
Idioma do texto original: inglês
Review or implement a security-sensitive change by tracing assets, actors, trust boundaries, abuse paths, controls, and verification evidence. Use for threat models and security gates, or when changing authentication, authorization, untrusted input or files,…
Idioma do texto original: inglês