Menú
SkillsMP ha recopilado 11 skills de atomicstrata/epistemic. Abre una skill para revisar su origen y sus detalles.
Mostrando 11 de 11 skills recopiladas.
Use when a research idea, vague comparison, or surprising observation must be turned into a falsifiable, prereg-ready hypothesis before any benchmark, eval, training, or judge-backed work begins.
Idioma del texto original: inglés
Use when starting a research, eval, benchmark, or empirical comparison session - explains how to activate Epistemic skills, choose stage skills, and enforce research gates before any experiment work.
Idioma del texto original: inglés
Use when starting or continuing empirical/ML research, evals, benchmarks, or any "is X better than Y?" claim — the umbrella mechanism that enforces hypothesis → preregistration → baseline → experiment → statistical rigor → falsification → kill-or-ship →…
Idioma del texto original: inglés
Use when a claim, result, or draft compares your system against an external baseline, published paper number, or competitor result and you need a sourced local reproduction before quoting it.
Idioma del texto original: inglés
Use when a preregistered hypothesis is ready to run and you must generate provisional evidence under the locked method without contaminating headline outputs.
Idioma del texto original: inglés
Use when a hypothesis has reached a real decision point and you must choose KILL, PIVOT, RECOMMIT, REFINE, or SHIP from repository evidence.
Idioma del texto original: inglés
Use when a hypothesis is concrete enough to freeze the experiment contract, lock the judge and compute environment, and scaffold the run before any experiment-shaped command executes.
Idioma del texto original: inglés
Use when completed experiment outputs exist in `experiments/{id}/smokes/` and the agent must decide whether an inferential claim is statistically defensible before falsification review or promotion.
Idioma del texto original: inglés
Use when about to state, circulate, merge, or publish any research result, comparison claim, or confirmed conclusion.
Idioma del texto original: inglés
Use when a numerical claim, comparison claim, or headline result is about to leave `smokes/` or be written into `RESULTS.md`.
Idioma del texto original: inglés
Quarantine and explain any result that diverges from the most recent prior result on the same benchmark by more than 15% before it leaves `smokes/`.
Idioma del texto original: inglés