Agent skill

Dftbplus

by Hello-QM in Hello-QM/catgo-LRG

Generate and manage DFTB+ calculations. An agent skill from Hello-QM/catgo-LRG.

AGPL-3.0Auto-check passed

Install Dftbplus

skills CLI
$ npx skills add Hello-QM/catgo-LRG --skill dftbplus -a claude-code

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

GitHub CLI
$ gh skill install Hello-QM/catgo-LRG dftbplus --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/Hello-QM/catgo-LRG.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dftbplus .claude/skills/dftbplus && 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
dftbplus
GitHub stars
205
Token cost
~1.1k tokens
SKILL.md length
321 words
Files
1
Skills in repo
75
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate and manage DFTB+ calculations. An agent skill from Hello-QM/catgo-LRG.

  • Works in 3 steps: Verify structure → Create workflow → Add DFTB+ task via shell
  • The user requests DFTB+
  • SKILL.md covers When to Use, Prerequisites, Workflow Steps and Input File Template — SCC-DFTB…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dftbplus is an agent skill from Hello-QM/catgo-LRG. Generate and manage DFTB+ calculations. Use when the user requests DFTB+, tight-binding DFT, SCC-DFTB, or needs fast approximate DFT for large systems or MD.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires DFTB+ installed on the HPC target. Slater-Koster parameter files must be available (e.g., 3ob, matsci, mio sets from dftb.org).

The repository describes itself as: AI-driven workbench for computational materials science — interactive 3D structure viewer, natural-language CatBot assistant, visual DAG workflow engine, HPC job submission… The licence is AGPL-3.0.

When your agent uses it

  • The user requests DFTB+
  • Tight-binding DFT
  • Needs fast approximate DFT for large systems

Example prompts

  • “/dftbplus”

Requirements

  • Compatibility (from SKILL.md): Requires DFTB+ installed on the HPC target. Slater-Koster parameter files must be available (e.g., 3ob, matsci, mio sets from dftb.org).

Workflow steps

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

  1. Verify structure
  2. Create workflow
  3. Add DFTB+ task via shell

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.

    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 DFTB+ installed on the HPC target. Slater-Koster parameter files must be available (e.g., 3ob, matsci, mio sets from dftb.org).

    From compatibility in the SKILL.md frontmatter.

Context cost

Dftbplus loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
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

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 Hello-QM/catgo-LRG at commit fd6291b, republished under its AGPL-3.0 licence (© Hello-QM). 321 words, ~1,089 tokens.

Download SKILL.mdSave it as .claude/skills/dftbplus/SKILL.md (or your agent's skills folder).
name
dftbplus
description
Generate and manage DFTB+ calculations. Use when the user requests DFTB+, tight-binding DFT, SCC-DFTB, or needs fast approximate DFT for large systems or MD.
compatibility
Requires DFTB+ installed on the HPC target. Slater-Koster parameter files must be available (e.g., 3ob, matsci, mio sets from dftb.org).

DFTB+

When to Use

  • User explicitly requests DFTB+ or tight-binding DFT
  • User needs fast DFT-level calculations for large systems (1000-10000 atoms)
  • User wants SCC-DFTB molecular dynamics at DFT accuracy
  • User needs a quick pre-screening before expensive DFT
  • User has Slater-Koster parameters available for the elements of interest

Prerequisites

  1. DFTB+ binary accessible on HPC (dftb+ --version)
  2. Slater-Koster files available (3ob for organic/bio, matsci for inorganic, mio for general)
  3. Structure loaded in viewer — verify with catgo_view(action="get_state")
  4. Confirm SK parameter coverage for all elements in the structure

Workflow Steps

1. Verify structure
catgo_view(action="get_state")
2. Create workflow
catgo_workflow_engine(action="create", params={"name": "DFTB+ optimization"})
3. Add DFTB+ task via shell

CatGo does not yet have a native DFTB+ engine. Use task_type: "shell".

catgo_workflow_engine(action="add_task", params={
  "workflow_id": "wf_xxx",
  "task_type": "shell",
  "name": "dftb_relax",
  "command": "dftb+ > dftb.out 2>&1",
  "input_files": {
    "dftb_in.hsd": "<HSD input content>",
    "geo.gen": "<geometry in GEN format>"
  },
  "system_name": "MoS2_relax"
})

When a @register_engine("dftbplus") is added, use task_type: "geo_opt" with software: "dftbplus".

Input File Template — SCC-DFTB SCF

Geometry = GenFormat {
  <<< geo.gen
}

Driver = {}

Hamiltonian = DFTB {
  Scc = Yes
  SccTolerance = 1e-5
  MaxSccIterations = 200

  SlaterKosterFiles = Type2FileNames {
    Prefix = "/path/to/skfiles/3ob-3-1/"
    Separator = "-"
    Suffix = ".skf"
  }

  MaxAngularMomentum {
    Ti = "d"
    O  = "p"
  }

  KPointsAndWeights = SupercellFolding {
    <k1> 0 0
    0 <k2> 0
    0 0 <k3>
    0.0 0.0 0.0
  }

  Filling = Fermi {
    Temperature [K] = 300
  }
}

Options {
  WriteDetailedOut = Yes
}

Analysis {
  CalculateForces = Yes
}

Relaxation Input

Replace Driver = {} with:

Driver = ConjugateGradient {
  MaxForceComponent = 1e-3   # Ha/Bohr (~0.05 eV/Ang)
  MaxSteps = 500
  LatticeOpt = No            # Yes for bulk cell optimization
}

GEN Format (Geometry File)

<natoms> S                    # S=supercell (periodic), C=cluster
Ti O                          # Element labels
1  1  0.000  0.000  0.000     # index, type, x, y, z (Angstrom or Bohr)
2  2  1.479  1.479  0.000
0.0 0.0 0.0                   # Origin
<a1x> <a1y> <a1z>             # Lattice vectors (only for S type)
<a2x> <a2y> <a2z>
<a3x> <a3y> <a3z>

Parameter Guidance

ParameterTypical valueNotes
SccTolerance1e-5SCC charge convergence; tighten for forces
MaxAngularMomentumPer elementMust match SK files (s/p/d/f)
SlaterKosterFiles3ob / matsci / mioCheck element coverage at dftb.org
MaxForceComponent1e-3 Ha/Bohr~0.05 eV/Ang; 1e-4 for high accuracy
Filling Temperature300 KElectronic smearing; increase for metals

Slater-Koster Parameter Sets

SetElementsBest for
3ob-3-1H, C, N, O, S, P, Zn, ...Organic, biochemistry
matsci-0-3Si, Ge, C, ...Semiconductors, materials
mio-1-1H, C, N, O, S, PGeneral organic
tiorg-0-1Ti, C, H, N, O, STiO2 + organics

Common Pitfalls

  1. Missing SK files — DFTB+ silently produces wrong results if SK files are incomplete. Verify all element pairs exist.
  2. MaxAngularMomentum mismatch — must exactly match what the SK file provides (check SK file header)
  3. No SK files for element pair — DFTB+ cannot treat arbitrary element combinations. Check dftb.org/parameters.
  4. Units — DFTB+ uses atomic units internally (Bohr, Hartree). GEN files use Angstrom by default.
  5. Dispersion missing — add Dispersion = DftD3 {} for van der Waals systems
  6. Spin polarization — add SpinPolarisation = Colinear { ... } for magnetic systems; not all SK sets support it

© 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/dftbplus of Hello-QM/catgo-LRG.

Open the folder on GitHubat commit fd6291b

Compare with similar skills

Dftbplus 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.

Dftbplus compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dftbplus this skillHello-QM/catgo-LRG205—~1.1kAutomated safety check: PassAGPL-3.0
Eol Resistor Calculatorsickn33/agentic-awesome-skills47k1 repos~3.5kAutomated safety check: PassMIT
Metric Calculatorjeremylongshore/tons-of-skills-marketplace2.8k—~563Automated safety check: PassMIT
Retention Calculatorjeremylongshore/tons-of-skills-marketplace2.8k—~573Automated safety check: PassMIT
Throughput Calculatorjeremylongshore/tons-of-skills-marketplace2.8k—~577Automated safety check: PassMIT
CalculatorCode-and-Sorts/awesome-copilot-agents5791 repos~470Automated safety check: PassMIT

Similar skills

  • Eol Resistor Calculator

    sickn33/agentic-awesome-skills

    Calculates and validates end-of-line (EOL, SEOL, DEOL, TEOL) resistor loops for intrusion alarm panels (Honeywell, DSC, Paradox, Bosch) with wire gauge drop and state tables.

    47k GitHub starsUsed in 1 repo~3.5k tokens
    Auto-check passed
  • Metric Calculator

    jeremylongshore/tons-of-skills-marketplace

    Configure and manage - Calculate metric calculator operations.

    2.8k GitHub stars~563 tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Retention Calculator

    jeremylongshore/tons-of-skills-marketplace

    Configure and manage - Calculate retention calculator operations.

    2.8k GitHub stars~573 tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Throughput Calculator

    jeremylongshore/tons-of-skills-marketplace

    Calculate throughput calculator operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~577 tokensUpdated today
    Testing & QAAuto-check passed
  • Calculator

    Code-and-Sorts/awesome-copilot-agents

    Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents.

    579 GitHub starsUsed in 1 repo~470 tokens
    Auto-check passed
  • Statistical Significance Calculator

    jeremylongshore/tons-of-skills-marketplace

    Configure and manage - Calculate statistical significance calculator operations.

    2.8k GitHub starsUsed in 1 repo~619 tokens
    Marketing & SEOAuto-check passed

More from Hello-QM/catgo-LRG

All 75 skills in this repo
  • Campaign Md Orchestration

    Hello-QM/catgo-LRG

    Drive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB).

    205 GitHub stars~1.6k tokensUpdated 16 days ago
    Auto-check passed
  • Lammps Deepmd

    Hello-QM/catgo-LRG

    Run LAMMPS molecular dynamics with DeePMD-kit machine learning potentials.

    205 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Catgo Gibbs Pipeline

    Hello-QM/catgo-LRG

    Compute adsorption/reaction Gibbs free energies, free-energy diagrams, and electrochemical overpotentials (HER/ORR/OER/CO2RR/NRR) with VASP.

    205 GitHub stars~669 tokensUpdated 16 days ago
    Auto-check passed
  • Abinit

    Hello-QM/catgo-LRG

    Generate and manage ABINIT DFT calculations. An agent skill from Hello-QM/catgo-LRG.

    205 GitHub stars~963 tokensUpdated 16 days ago
    Auto-check passed
  • Adsorbate Placement

    Hello-QM/catgo-LRG

    A skill your agent uses when the user asks to place an adsorbate molecule on a surface, find adsorption sites, or set up a surface+adsorbate model for DFT.

    205 GitHub stars~3k tokensUpdated 16 days ago
    Auto-check passed
  • Adsorption Energy

    Hello-QM/catgo-LRG

    A skill your agent uses when the user asks for adsorption energy, binding energy, or wants to compare how strongly a molecule binds to a surface.

    205 GitHub stars~1.4k tokensUpdated 16 days ago
    Auto-check passed

Questions about Dftbplus

What does Dftbplus do?

Generate and manage DFTB+ calculations. An agent skill from Hello-QM/catgo-LRG. Dftbplus is an agent skill from Hello-QM/catgo-LRG. Generate and manage DFTB+ calculations.

When should I use Dftbplus?

Dftbplus fits situations like: the user requests DFTB+; tight-binding DFT; needs fast approximate DFT for large systems.

How do I install Dftbplus in Claude Code?

Run `npx skills add Hello-QM/catgo-LRG --skill dftbplus -a claude-code`. Or copy the skill folder (.claude/skills/dftbplus in Hello-QM/catgo-LRG) into .claude/skills/dftbplus in your project. Claude Code loads it when a task matches its description.

How do I install Dftbplus in Codex?

Run `npx skills add Hello-QM/catgo-LRG --skill dftbplus -a codex`. Or copy the skill folder (.claude/skills/dftbplus in Hello-QM/catgo-LRG) into .agents/skills/dftbplus in your project. Codex loads it when a task matches its description.

Can I use Dftbplus 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 Hello-QM/catgo-LRG --skill dftbplus -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dftbplus, .gemini/skills/dftbplus, .github/skills/dftbplus and .opencode/skills/dftbplus in your project.

What does Dftbplus need to run?

SKILL.md names no scripts, command-line tools or credentials: Dftbplus is instructions for the agent only. Compatibility (from SKILL.md): Requires DFTB+ installed on the HPC target. Slater-Koster parameter files must be available (e.g., 3ob, matsci, mio sets from dftb.org). .

Does Dftbplus 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 Dftbplus 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 Dftbplus use?

Dftbplus is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dftbplus use?

About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dftbplus?

Skills that share tags, products or a category with Dftbplus: Eol Resistor Calculator (sickn33/agentic-awesome-skills, 47k stars), Metric Calculator (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Retention Calculator (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Throughput Calculator (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dftbplus?

Hello-QM (a GitHub user) maintains it in Hello-QM/catgo-LRG, which has 205 GitHub stars. The repository holds 75 skills in this directory. The repository was last updated on September 22, 2026.

Source: Hello-QM/catgo-LRG on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.