All authors
Claude Skills by JinukMoon
github.com/JinukMoon5 skills0 installs4 views
- CatbenchRun the full-roster catbench adsorption benchmarking pipeline across oh-my-mlip models. Triggers on requests to benchmark, compare, or evaluate MLIPs on catalysis/adsorption tasks — including generic phrasing like "benchmark several machine-learning potentials on my adsorption dataset" — even when "oh-my-mlip" or "catbench" is not named. Do NOT trigger on literature-only comparison questions with no dataset/compute intent.Votes: 0GitHub stars: 3
- DistillDistill any oh-my-mlip teacher MLIP into a CPU-deployable LAMMPS NN-MTP student via the onthefly-distill (GPL-2.0, orchestrated sibling repo) active-learning loop. Triggers on requests to distill, compress, or convert a foundation MLIP into a fast LAMMPS potential — "distill MACE into a LAMMPS student", "onthefly-distill", "NN-MTP student", "AL loop for a student potential", "shrink this teacher into something CPU-deployable" — even when "oh-my-mlip" or "distill" is not named.Votes: 0GitHub stars: 3
- FinetuneFine-tune an oh-my-mlip model on your own dataset from a foundation checkpoint. Triggers on requests to fine-tune, continue training, or adapt a model to custom data — "fine-tune MACE on my data", "continue training SevenNet", "train DeePMD with my extxyz frames" — even when "oh-my-mlip" or "finetune" is not named.Votes: 0GitHub stars: 3
- RunRun a single-point energy/forces calculation or structure relaxation with any oh-my-mlip MLIP. Triggers on requests to run, compute, calculate, or relax a structure with a specific model (MACE, SevenNet, NequIP, ORB, etc.) via oh-my-mlip. Also triggers on GENERIC natural-language compute intent — "single-point this structure with an MLIP", "relax this POSCAR with a machine-learning (interatomic) potential / ML force field" — even when no specific model and no "oh-my-mlip" is named; when no mo...Votes: 0GitHub stars: 3
- SetupInstall an oh-my-mlip MLIP model environment and verify energy+force on GPU. Triggers on requests to "install", "set up", "setup", or "get working" any MLIP model (MACE, SevenNet, NequIP, Allegro, ORB, UMA, etc.) via oh-my-mlip. Also triggers when a user wants to run a model for the first time and the env is not yet materialized. Also triggers on GENERIC natural-language intent to use a machine-learning interatomic potential — "set up an MLIP", "install an ML potential / machine-learned force...Votes: 0GitHub stars: 3