New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Quantum ESPRESSO DFT Task Builder

by jinzhezenggroup in jinzhezenggroup/computational-chemistry-agent-skills

Turns a user-supplied atomic structure and DFT settings into a runnable Quantum ESPRESSO input file, stopping short of submitting the job.

LGPL-3.0-or-laterAuto-check passedResearch & Science

Install Quantum ESPRESSO DFT Task Builder

skills CLI
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill dft-qe -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills dft-qe --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/quantum-chemistry/dft-qe .claude/skills/dft-qe && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dft-qe
GitHub stars
148
Token cost
~1.8k tokens
SKILL.md length
805 words
Files
3 (incl. references, assets)
Skills in repo
62
Repo updated
First seen
Licence
LGPL-3.0-or-later

At a glance

Turns a user-supplied atomic structure and DFT settings into a runnable Quantum ESPRESSO input file, stopping short of submitting the job.

  • Works in 7 steps: Start from a user-provided structure. → Normalize the structure into the task… → Determine the target QE calculation type. → …
  • Preparing a Quantum ESPRESSO SCF or relax input from a structure file
  • SKILL.md covers Scope, Hard requirement, Structure input convention and Expected workflow, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

A structure from the user is a hard requirement; the skill stops and asks rather than generating a task without one. It normalizes the structure into a staging layout, converting formats through a separate dpdata-cli skill when needed, and for periodic systems keeps the cell information even when a plain xyz file needs a separate CELL file to carry it. It then works out the calculation type, whether SCF, NSCF, relax, vc-relax, MD, bands, DOS or phonons.

Only the missing critical DFT parameters are collected, such as `calculation`, `input_dft`, `ecutwfc`, `pseudo_dir` and a pseudopotential for each element, with items like `vdw_corr` confirmed rather than guessed when dispersion might matter. The generated input follows the bundled example at `assets/pw-water-0.in`, lands in a runnable task directory, and states any assumptions or open choices. Submission itself is left to a separate skill such as `dpdisp-submit`.

When your agent uses it

  • Preparing a Quantum ESPRESSO SCF or relax input from a structure file
  • Building a QE phonon or bands calculation with specific cutoffs
  • Converting a structure into a QE-ready task directory before submission

Example prompts

  • “Build a QE vc-relax input from this water structure with a 60 Ry cutoff.”
  • “Set up a phonon calculation for this structure and ask about missing settings.”
  • “Prepare a QE bands calculation and hand it off to dpdisp-submit when done.”

Requirements

  • A user-provided structure file
  • Pseudopotential files for each element
  • Compatibility (from SKILL.md): Requires a user-provided initial structure and enough DFT parameters to build a scientifically meaningful QE input.

Workflow steps

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

  1. Start from a user-provided structure.
  2. Normalize the structure into the task layout if needed.
  3. Determine the target QE calculation type.
  4. Collect only the missing critical DFT parameters.
  5. Generate the QE input file.
  6. Place the generated task in a runnable task directory.
  7. If submission is requested, pass that directory to dpdisp-submit.

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

    No scripts in the folder and no shell commands in SKILL.md.

    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 a user-provided initial structure and enough DFT parameters to build a scientifically meaningful QE input.

    From compatibility in the SKILL.md frontmatter.

Context cost

Quantum ESPRESSO DFT Task Builder loads about 1.8k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 805 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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). 805 words, ~1,752 tokens.

Download SKILL.mdSave it as .claude/skills/dft-qe/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
dft-qe
description
Generate Quantum ESPRESSO DFT input tasks from a user-provided structure plus user-specified DFT settings. Use when the user wants to prepare QE calculations such as SCF, NSCF, relax, vc-relax, MD, bands, DOS, or phonons starting from a structure file or coordinates together with pseudopotentials, functional choice, cutoffs, k-point settings, smearing, spin/charge, and convergence parameters. This skill prepares the QE task only; use a separate submission skill such as dpdisp-submit to submit the generated task.
compatibility
Requires a user-provided initial structure and enough DFT parameters to build a scientifically meaningful QE input.
license
LGPL-3.0-or-later
metadata.author
Yi-FanLi
metadata.version
1.0
metadata.repository
https://gitlab.com/QEF/q-e
metadata.qe_docs
https://www.quantum-espresso.org/Doc/user_guide/

DFT with Quantum ESPRESSO

Use this skill to build a QE DFT task from a user-provided structure and DFT settings.

Scope

This skill should:

  • require a user-provided structure
  • read or normalize the structure input
  • identify the target calculation type
  • collect the minimum required DFT settings
  • generate the QE input file
  • organize the task directory in a way that can be handed off to a submission skill
  • state assumptions and unresolved choices

This skill should not:

  • submit jobs
  • manage schedulers
  • handle remote execution
  • invent critical scientific parameters

If the user wants the task submitted, hand off to another skill such as dpdisp-submit after the QE task is generated.

Hard requirement

The user must provide a structure.

Do not generate a QE task without a user-provided structure source. If the structure is missing, stop and ask for it.

Structure input convention

Use this bundled example-plus-layout pattern as the reference:

  • generated QE input example: assets/pw-water-0.in
  • user-provided structure staging pattern: openclaw_input/ containing files such as structure.xyz and CELL

Treat this as the canonical pattern for what the user is expected to provide and what this skill is expected to generate.

The structure format does not need to be fixed to xyz. If the user provides another reasonable atomistic structure format, convert or normalize it as needed. When format conversion is needed, use the dpdata-cli skill.

For periodic systems, ensure cell information is preserved. If a plain xyz file is used, cell data must be provided separately, for example through a CELL file.

For a concrete file-oriented workflow, see references/commands-and-workflow.md.

Expected workflow

  1. Start from a user-provided structure.
  2. Normalize the structure into the task layout if needed.
  3. Determine the target QE calculation type.
  4. Collect only the missing critical DFT parameters.
  5. Generate the QE input file.
  6. Place the generated task in a runnable task directory.
  7. If submission is requested, pass that directory to dpdisp-submit.

DFT parameters to collect

Must provide

Do not generate a formal QE task unless these are known or explicitly confirmed:

  • calculation
  • input_dft
  • ecutwfc
  • pseudo_dir
  • pseudopotential file for each element
Usually should be explicit

These should normally be confirmed rather than guessed:

  • vdw_corr when dispersion may matter
  • ecutrho when relevant to the pseudopotential family or workflow
  • K_POINTS setting, for example gamma or an automatic mesh
  • occupation / smearing settings for metallic or ambiguous systems
  • conv_thr
  • electron_maxstep
Task-specific additions

Also collect task-dependent parameters when relevant.

For relax / vc-relax:

  • forc_conv_thr
  • etot_conv_thr
  • cell_dofree for vc-relax

For md:

  • nstep
  • dt
  • ion_temperature
  • tempw
  • ion_dynamics

For spin-polarized or magnetic systems:

  • nspin
  • starting_magnetization
  • charge or spin-related settings if requested

For advanced workflows if explicitly requested:

  • Hubbard U settings
  • hybrid-functional settings
  • electric field settings such as edir, emaxpos, or related controls

Do not ask for everything at once; ask only for the missing essentials.

Show full SKILL.md (347 more words)Show less

Required behavior

  1. Inspect the provided structure if accessible.
  2. Determine elements, cell information, and coordinate representation.
  3. If format normalization is needed, convert the structure using dpdata-cli.
  4. Confirm the QE task type.
  5. Gather only the missing critical DFT settings.
  6. Generate the QE input yourself.
  7. Explain assumptions clearly.
  8. Flag unresolved scientific choices instead of hiding them.
  9. Prepare the task directory so another skill can submit it.

Template pattern

Use the QE example input included in this repository:

assets/pw-water-0.in

as the reference pattern for how a QE task is organized and how the pw.x input is laid out.

In this workflow:

  • the user provides the structure in openclaw_input-style form
  • this skill generates the QE input task, analogous to files like assets/pw-water-0.in
  • a separate submission skill handles the job script and submission stage

Do not hard-code the example chemistry. Reuse only the workflow pattern.

Defaulting policy

Allowed only for low-risk, clearly labeled assumptions.

Reasonable provisional defaults:

  • calculation='scf' for a plain single-point request
  • standard electronic convergence threshold when the user does not care
  • basic verbosity settings

Do not silently invent:

  • structure data
  • pseudopotential filenames
  • production cutoffs
  • production k-point meshes
  • magnetic state for open-shell systems
  • Hubbard / vdW / hybrid settings
  • metallic smearing behavior when the system character is unclear

Expected output

Provide:

  1. the full QE input file
  2. a short summary of the chosen settings
  3. explicit assumptions
  4. any decisions the user should still confirm
  5. the generated task directory or file set for the next skill
  6. if submission is requested, explicitly say the next step is dpdisp-submit

Minimal pw.x structure

text
&CONTROL
  calculation = 'scf'
  prefix = 'system'
  outdir = './'
/
&SYSTEM
  ibrav = 0
  nat = ...
  ntyp = ...
  ecutwfc = ...
  ecutrho = ...
/
&ELECTRONS
  conv_thr = 1.0d-8
/
ATOMIC_SPECIES
...
CELL_PARAMETERS angstrom
...
ATOMIC_POSITIONS angstrom
...
K_POINTS automatic
kx ky kz 0 0 0

Handoff rule

When the user asks to submit the generated QE task, do not implement submission logic here. Instead:

  • finish generating the QE task directory and input file
  • tell the user the task is ready for submission
  • hand off to dpdisp-submit

Common failure points

  • missing user-provided structure
  • missing cell for periodic systems
  • incomplete pseudopotential mapping
  • nat / ntyp inconsistent with the structure
  • missing or poor cutoffs
  • missing or inappropriate smearing
  • omitted spin settings for magnetic cases
  • requesting post-processing or phonons without prerequisite context

© 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 2 other files (references, assets) in quantum-chemistry/dft-qe of jinzhezenggroup/computational-chemistry-agent-skills.

  • SKILL.md
  • assets/pw-water-0.in
  • references/commands-and-workflow.md

Open the folder on GitHubat commit 5c19e75

Compare with similar skills

Quantum ESPRESSO DFT Task Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Quantum ESPRESSO DFT Task Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Quantum ESPRESSO DFT Task Builder this skilljinzhezenggroup/computational-chemistry-agent-skills148—~1.8kAutomated safety check: PassLGPL-3.0-or-later
AstropyzLanqing/codex-claude-academic-skills4.7k13 repos~2.9kAutomated safety check: PassBSD-3-Clause
PymatgenzLanqing/codex-claude-academic-skills4.7k11 repos~5kAutomated safety check: PassMIT
Cantera Ignition DelayK-Dense-AI/scientific-agent-skills48k1 repos~2.2kAutomated safety check: PassMIT
Weathertrpc-group/trpc-agent-go1.9k8 repos~591Automated safety check: PassApache-2.0
Pymol VisualizationChatMol/ChatMol373—~1.2kAutomated safety check: PassMIT

Similar skills

  • Astropy

    zLanqing/codex-claude-academic-skills

    Comprehensive Python library for astronomy and astrophysics.

    4.7k GitHub starsUsed in 13 repos~2.9k tokens
    Research & ScienceAuto-check passed

  • Pymatgen

    zLanqing/codex-claude-academic-skills

    Materials science toolkit. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 11 repos~5k tokens
    Research & ScienceAuto-check passed

  • Cantera Ignition Delay

    K-Dense-AI/scientific-agent-skills

    Runs Cantera constant-volume or constant-pressure ignition simulations and reports temperature-based ignition delay with mechanism provenance and checks.

    48k GitHub starsUsed in 1 repo~2.2k tokens
    Research & ScienceAuto-check passed

  • Weather

    trpc-group/trpc-agent-go

    Get current weather and forecasts via wttr.in or Open-Meteo.

    1.9k GitHub starsUsed in 8 repos~591 tokens
    Research & ScienceAuto-check passed

  • Pymol Visualization

    ChatMol/ChatMol

    Generate publication-quality molecular visualization images using PyMOL.

    373 GitHub stars~1.2k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed

  • Review

    Muuuun/luxas

    Write domain-authentic review articles that synthesize rather than stack.

    1.2k GitHub stars~2.1k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from jinzhezenggroup/computational-chemistry-agent-skills

All 62 skills in this repo

  • DP-GEN Simplify Workflow

    jinzhezenggroup/computational-chemistry-agent-skills

    Prepares, validates and runs DP-GEN simplify jobs that thin out repeated or redundant DeepMD datasets, generating param.json and machine.json for local or scheduler runs.

    148 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed

  • LAMMPS with DeePMD-kit

    jinzhezenggroup/computational-chemistry-agent-skills

    Prepares and runs molecular dynamics simulations in LAMMPS with a DeePMD machine-learning potential, writing the input script and choosing NVE, NVT or NPT.

    148 GitHub stars~2.8k tokensUpdated 2 days ago
    Auto-check passed

  • LAMMPS ReaxFF Setup

    jinzhezenggroup/computational-chemistry-agent-skills

    Prepares and explains LAMMPS input scripts for reactive molecular dynamics with the ReaxFF potential, including charge equilibration and ensemble choice.

    148 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed

  • RDKit Conformer Generator

    jinzhezenggroup/computational-chemistry-agent-skills

    Generates 3D molecular conformers from SMILES strings or files with RDKit, keeps the lowest-energy one per molecule, and falls back to 2D coordinates when embedding fails.

    148 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed

  • RDKit Descriptors and Fingerprints

    jinzhezenggroup/computational-chemistry-agent-skills

    Computes RDKit physicochemical descriptors and molecular fingerprints from SMILES through a uv-run CLI script that skips and logs invalid molecules.

    148 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed

  • Unimol

    jinzhezenggroup/computational-chemistry-agent-skills

    A standardized CLI wrapper for Uni-Mol molecular ML workflows that handles representation extraction (embeddings), model training (regression/classification), and property prediction with built-in…

    148 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Quantum ESPRESSO DFT Task Builder

What does Quantum ESPRESSO DFT Task Builder do?

Turns a user-supplied atomic structure and DFT settings into a runnable Quantum ESPRESSO input file, stopping short of submitting the job. A structure from the user is a hard requirement; the skill stops and asks rather than generating a task without one. It normalizes the structure into a staging layout, converting formats through a separate dpdata-cli skill when needed, and for periodic systems keeps the cell information even when a plain xyz file needs a separate CELL file to carry it.

When should I use Quantum ESPRESSO DFT Task Builder?

Quantum ESPRESSO DFT Task Builder fits situations like: preparing a Quantum ESPRESSO SCF or relax input from a structure file; building a QE phonon or bands calculation with specific cutoffs; converting a structure into a QE-ready task directory before submission.

How do I install Quantum ESPRESSO DFT Task Builder in Claude Code?

Run `npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill dft-qe -a claude-code`. Or copy the skill folder (quantum-chemistry/dft-qe in jinzhezenggroup/computational-chemistry-agent-skills) into .claude/skills/dft-qe in your project. Claude Code loads it when a task matches its description.

How do I install Quantum ESPRESSO DFT Task Builder in Codex?

Run `npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill dft-qe -a codex`. Or copy the skill folder (quantum-chemistry/dft-qe in jinzhezenggroup/computational-chemistry-agent-skills) into .agents/skills/dft-qe in your project. Codex loads it when a task matches its description.

Can I use Quantum ESPRESSO DFT Task Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill dft-qe -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dft-qe, .gemini/skills/dft-qe, .github/skills/dft-qe and .opencode/skills/dft-qe in your project.

What does Quantum ESPRESSO DFT Task Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Quantum ESPRESSO DFT Task Builder is instructions for the agent only. Our summary lists: A user-provided structure file; Pseudopotential files for each element. Compatibility (from SKILL.md): Requires a user-provided initial structure and enough DFT parameters to build a scientifically meaningful QE input..

Does Quantum ESPRESSO DFT Task Builder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Quantum ESPRESSO DFT Task Builder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Quantum ESPRESSO DFT Task Builder use?

Quantum ESPRESSO DFT Task Builder is published under the LGPL-3.0-or-later licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Quantum ESPRESSO DFT Task Builder use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 552 tokens, read only when the agent opens those files.

What are the alternatives to Quantum ESPRESSO DFT Task Builder?

Skills that share tags, products or a category with Quantum ESPRESSO DFT Task Builder: Astropy (zLanqing/codex-claude-academic-skills, 4.7k stars), Pymatgen (zLanqing/codex-claude-academic-skills, 4.7k stars), Cantera Ignition Delay (K-Dense-AI/scientific-agent-skills, 48k stars) and Weather (trpc-group/trpc-agent-go, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Quantum ESPRESSO DFT Task Builder?

jinzhezenggroup (a GitHub organization) maintains it in jinzhezenggroup/computational-chemistry-agent-skills, which has 148 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 9, 2026.

Source: jinzhezenggroup/computational-chemistry-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.