Dpdata

What it does

Example prompts

• “/dpdata”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires dpdata Python package (pip install dpdata). Works on any platform.

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Missing type_map for LAMMPS — LAMMPS dump files have numeric types, not element names. Always provide type_map.
2. 2Unconverged frames — VASP OUTCARs may contain unconverged ionic steps. Filter by force magnitude before training.
3. 3Mixed element order — when merging data from different calculations, ensure consistent element ordering.
4. 4Large memory for big trajectories — dpdata loads all frames into memory. For >10K frames, process in chunks.
5. 5Units — dpdata converts to eV/Angstrom internally. LAMMPS real units are auto-converted.

What it can do on your machine

Read from SKILL.md and the folder at commit fd6291b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • pip
  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires dpdata Python package (pip install dpdata). Works on any platform.

  From compatibility in the SKILL.md frontmatter.

Context cost

Dpdata loads about 1.1k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 257 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~47

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 257 words, ~1,075 tokens.

name

dpdata

description

Convert between computational chemistry data formats using dpdata. Handles VASP, QE, CP2K, Gaussian, LAMMPS, and DeePMD formats. Essential for preparing ML potential training data.

compatibility

Requires dpdata Python package (pip install dpdata). Works on any platform.

catalog-hidden

true

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "convert_data",
  "command": "python convert.py",
  "input_files": {
    "convert.py": "import dpdata\nd = dpdata.LabeledSystem('OUTCAR', fmt='vasp/outcar')\nd.to('deepmd/npy', 'training_data')"
  },
  "system_name": "data_prep"
})

import dpdata
import numpy as np

# Load all frames from OUTCAR
d = dpdata.LabeledSystem("OUTCAR", fmt="vasp/outcar")
print(f"Loaded {len(d)} frames")

# Random split: 90% train, 10% valid
indices = np.random.permutation(len(d))
n_train = int(0.9 * len(d))

d_train = d.sub_system(indices[:n_train])
d_valid = d.sub_system(indices[n_train:])

d_train.to("deepmd/npy", "data/train")
d_valid.to("deepmd/npy", "data/valid")
print(f"Train: {len(d_train)}, Valid: {len(d_valid)}")

import dpdata
from pathlib import Path

d = None
for outcar in Path(".").rglob("OUTCAR"):
    sys = dpdata.LabeledSystem(str(outcar), fmt="vasp/outcar")
    d = sys if d is None else d + sys

print(f"Total frames: {len(d)}")
d.to("deepmd/npy", "merged_data")

import dpdata
d = dpdata.LabeledSystem("relax.out", fmt="qe/pw/scf")
d.to("deepmd/npy", "training_data")

import dpdata
d = dpdata.System("dump.lammpstrj", fmt="lammps/dump",
                  type_map=["Ti", "O"])
d.to("extxyz", "trajectory.xyz")

import dpdata
import numpy as np

d = dpdata.LabeledSystem("OUTCAR", fmt="vasp/outcar")

# Remove frames with max force > 10 eV/Ang (likely unconverged)
mask = []
for i in range(len(d)):
    max_f = np.max(np.abs(d["forces"][i]))
    mask.append(max_f < 10.0)

d_clean = d.sub_system(np.where(mask)[0])
print(f"Kept {len(d_clean)}/{len(d)} frames")

# Quick convert
dpdata convert OUTCAR vasp/outcar deepmd/npy training_data

# System info
dpdata info OUTCAR vasp/outcar

© Hello-QM, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/dpdata of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Used in 1 other repository

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Hello-QM/catgo-LRG, which our catalogue first saw on October 7, 2026.

• majiayu000/claude-skill-registryskills/bash/dpdataskills/bash/dpdata-hello-qm-catgo-lrg