Phonopy

What it does

Example prompts

• “/phonopy”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires phonopy Python package (pip install phonopy). Requires a DFT code (VASP, QE, etc.) for force calculations on displaced structures.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Create supercells with displacements
2. 2Run DFT on each displaced structure
3. 3Collect forces and compute force constants
4. 4Compute phonon band structure

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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

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

• Network

  No URLs in SKILL.md.

  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 phonopy Python package (pip install phonopy). Requires a DFT code (VASP, QE, etc.) for force calculations on displaced structures.

  From compatibility in the SKILL.md frontmatter.

Context cost

Phonopy loads about 1.4k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 408 words of instructions outside code blocks.

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

~56

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

~1.4k

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). 408 words, ~1,393 tokens.

name

phonopy

description

Run phonon calculations using Phonopy. Computes phonon band structures, density of states, thermal properties, and checks dynamical stability. Works with VASP, QE, ABINIT, and other DFT codes as the force calculator.

compatibility

Requires phonopy Python package (pip install phonopy). Requires a DFT code (VASP, QE, etc.) for force calculations on displaced structures.

catalog-hidden

true

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "phonopy_displace",
  "command": "phonopy -d --dim 2 2 2 -c POSCAR",
  "input_files": {
    "POSCAR": "<relaxed structure>"
  },
  "system_name": "phonon_setup"
})

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "phonon_forces_001",
  "command": "cd disp-001 && vasp_std > vasp.out 2>&1",
  "depends_on": ["phonopy_displace"],
  "system_name": "phonon_disp_001"
})

PREC    = Accurate
ENCUT   = 520
EDIFF   = 1e-8      # Must be tight for phonons
IBRION  = -1
NSW     = 0
ISMEAR  = 0
SIGMA   = 0.05
LREAL   = .FALSE.    # Must be FALSE for phonons
LWAVE   = .FALSE.
LCHARG  = .FALSE.

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "phonopy_forces",
  "command": "phonopy -f disp-001/vasprun.xml disp-002/vasprun.xml ...",
  "depends_on": ["phonon_forces_001", "phonon_forces_002"],
  "system_name": "phonon_fc"
})

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "phonopy_band",
  "command": "phonopy -p band.conf",
  "input_files": {
    "band.conf": "DIM = 2 2 2\nBAND = AUTO\nBAND_POINTS = 101\nBAND_LABELS = AUTO"
  },
  "depends_on": ["phonopy_forces"],
  "system_name": "phonon_band"
})

DIM = 2 2 2
BAND = AUTO
BAND_POINTS = 101

DIM = 2 2 2
MP = 20 20 20
TPROP = .TRUE.
TMIN = 0
TMAX = 1000
TSTEP = 10

DIM = 2 2 2
MP = 20 20 20
PDOS = 1 2, 3 4 5 6

import phonopy
from phonopy import Phonopy

ph = phonopy.load("phonopy_disp.yaml")
# Forces already set via phonopy -f

# Band structure
ph.auto_band_structure(plot=True)
ph.save("phonopy_results.yaml")

# Thermal properties
ph.run_mesh([20, 20, 20])
ph.run_thermal_properties(t_min=0, t_max=1000, t_step=10)
tp = ph.get_thermal_properties_dict()
# tp['temperatures'], tp['free_energy'], tp['entropy'], tp['heat_capacity']

© 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/phonopy of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b