メニュー
Route ABACUS requests to task-specific subskills based on user intent. Use when the user asks for any ABACUS DFT calculation and you need to determine whether the task is SCF, relaxation, MD, or electronic analysis.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/GodJh1n/GPUMD-skill --skill dft-abacusコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Route NEP requests to task-specific subskills. NEP (Neuroevolution Potential) is the native machine-learning potential family of the GPUMD ecosystem — analogous to DeePMD-kit for LAMMPS. Use when the user asks for `nep.in`, `train.xyz`, `test.xyz`, NEP training, NEP89 reuse, prediction mode, fine-tuning, dipole / polarizability auxiliary models, or automation via NepTrain / NepTrainKit.
Train a first NEP potential from labeled extxyz data. Use when the user needs `nep.in`, `train.xyz`, `test.xyz`, parameter guidance, loss.out interpretation, or deployment of the resulting `nep.txt` back into GPUMD. NEP is the native machine-learning potential for GPUMD and plays the role that DeePMD plays for LAMMPS.
Route VASP DFT requests to task-specific subskills based on user intent. Use when the user asks for VASP workflows and you must decide between static SCF, relaxation, DOS, or band-structure task preparation. This orchestration skill does not own detailed input generation logic; it dispatches to the correct VASP subskill and enforces consistent handoff to submission skills.
SOC 職業分類に基づく
SKILL.md を表示中
| name | dft-abacus |
| description | Route ABACUS requests to task-specific subskills based on user intent. Use when the user asks for any ABACUS DFT calculation and you need to determine whether the task is SCF, relaxation, MD, or electronic analysis. |
| compatibility | Requires a user-provided structure, compatible pseudopotentials/orbital files, and runnable ABACUS environment. |
| license | GPL-3.0-only |
| catalog-hidden | true |
| metadata | {"author":"qqgu","version":"0.2.0","repository":"https://github.com/deepmodeling/abacus-develop"} |
ABACUS (Atomic-orbital Based Ab-initio Computation at UStc) is an open-source DFT code supporting both PW (plane-wave) and LCAO (linear combination of atomic orbitals / numerical atomic orbital) basis sets. It is developed by the DeepModeling community and is tightly integrated with the DeePMD / NEP / dpdata ecosystem.
| User intent | Subskill |
|---|---|
| Single-point / total energy | dft-abacus/static |
| Relaxation (ion / cell) | dft-abacus/relax (planned) |
| Molecular dynamics | dft-abacus/md (planned) |
| Band / DOS / electronic | dft-abacus/electronic (planned) |
basis_type pw, behaves like QE.dpdata output support via out_level ie for NEP/DeePMD
training data generation.INPUT, STRU, KPT (not a single
input file like QE or CP2K).