Xtb

What it does

When your agent uses it

• The user asks for xTB calculations directly
• Wants to use xTB through Python/ASE/dpdata bridges while keeping xTB as the primary method rather than as an ASE-only backend

Example prompts

• “/xtb”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires a runnable xTB environment. Python-based workflows can use the `xtb` package; for reproducible ad hoc runs with uv, prefer `uv run --no-project --with ase --with xtb --with typing_extensions python ...` when using the ASE bridge.

Workflow steps

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

1. 1Direct xTB-oriented tasks
2. 2xTB through the ASE bridge
3. 3xTB through dpdata

What it can do on your machine

Read from SKILL.md and the folder at commit 5c19e75. 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:

  • uv

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

• Network

  No URLs in SKILL.md. Its commands use uv, 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 a runnable xTB environment. Python-based workflows can use the `xtb` package; for reproducible ad hoc runs with uv, prefer `uv run --no-project --with ase --with xtb --with typing_extensions python ...` when using the ASE bridge.

  From compatibility in the SKILL.md frontmatter.

Context cost

Xtb loads about 1.2k tokens when it runs, and up to ~1.9k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 411 words of instructions outside code blocks.

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

~88

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

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~1.9k

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 jinzhezenggroup/computational-chemistry-agent-skills at commit 5c19e75, republished under its LGPL-3.0-or-later licence (© jinzhezenggroup). 411 words, ~1,200 tokens.

name

xtb

description

Prepare and explain xTB semiempirical quantum-chemistry workflows for single-point energy, forces, charges, dipole, geometry optimization, and molecular dynamics. Use when the user asks for xTB calculations directly, or wants to use xTB through Python/ASE/dpdata bridges while keeping xTB as the primary method rather than as an ASE-only backend.

compatibility

Requires a runnable xTB environment. Python-based workflows can use the `xtb` package; for reproducible ad hoc runs with uv, prefer `uv run --no-project --with ase --with xtb --with typing_extensions python ...` when using the ASE bridge.

license

LGPL-3.0-or-later

metadata.author

njzjz-bot

metadata.version

1.0

metadata.repository

https://github.com/grimme-lab/xtb-python

from xtb.ase.calculator import XTB

uv run --no-project --with ase --with xtb --with typing_extensions python your_script.py

from ase.build import molecule
from xtb.ase.calculator import XTB

atoms = molecule("H2O")
atoms.calc = XTB(method="GFN2-xTB")
print(atoms.get_potential_energy())
print(atoms.get_forces())
print(atoms.get_charges())

from dpdata.system import System
from xtb.ase.calculator import XTB

sys = System("input.xyz", fmt="xyz")
ls = sys.predict(driver="ase", calculator=XTB(method="GFN2-xTB"))

from dpdata.driver import Driver
from dpdata.system import System
from xtb.ase.calculator import XTB

sys = System("input.xyz", fmt="xyz")
ase_driver = Driver.get_driver("ase")(calculator=XTB(method="GFN2-xTB"))
ls = sys.minimize(minimizer="ase", driver=ase_driver, fmax=0.05, max_steps=200)

© jinzhezenggroup, LGPL-3.0-or-later. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in quantum-chemistry/xtb of jinzhezenggroup/computational-chemistry-agent-skills.

• SKILL.md
• references/commands-and-workflow.md

Open the folder on GitHubat commit 5c19e75