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

Gjf Flux

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

Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files.

LGPL-3.0-or-laterAuto-check passedDevelopment

Install Gjf Flux

skills CLI
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill gjf-flux -a claude-code

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

GitHub CLI
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills gjf-flux --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/gjf-flux .claude/skills/gjf-flux && 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
gjf-flux
GitHub stars
148
Token cost
~2k tokens
SKILL.md length
652 words
Files
1
Skills in repo
62
Repo updated
First seen
Licence
LGPL-3.0-or-later

At a glance

Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files.

  • Works in 7 steps: Extract a section from a .gjf → Assemble directives (Link0 commands) → Assemble the route section (# line) → …
  • Needed for generating
  • SKILL.md covers When to use, Assumptions / Parsing model…, Inputs you should request from… and Core commands (cheat sheet), plus 4 more sections
  • Calls uvx

What it does

Gjf Flux is an agent skill from jinzhezenggroup/computational-chemistry-agent-skills. Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files. USE WHEN needed for generating, refactoring, templating, or scripting Gaussian job files.

Its SKILL.md is about 2k 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 uv installed and available in PATH.

It sits in Development, covering Refactoring. The repository describes itself as: Agent skills to run computational-chemistry tasks, used in OpenClaw. The licence is LGPL-3.0-or-later.

When your agent uses it

  • Needed for generating
  • Scripting Gaussian job files

Example prompts

  • “/gjf-flux”

Requirements

  • Compatibility (from SKILL.md): Requires `uv` installed and available in PATH.

Workflow steps

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

  1. Extract a section from a .gjf
  2. Assemble directives (Link0 commands)
  3. Assemble the route section (# line)
  4. Merge molecule fragments into one molecule block
  5. Assemble appendices
  6. Assemble a complete single-step .gjf
  7. Merge multiple tasks into a Link1 multi-step job

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:

    • uvx

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

  • Network

    No URLs in SKILL.md. Its commands use uvx, 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 `uv` installed and available in PATH.

    From compatibility in the SKILL.md frontmatter.

Context cost

Gjf Flux loads about 2k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 652 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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). 652 words, ~2,035 tokens.

Download SKILL.mdSave it as .claude/skills/gjf-flux/SKILL.md (or your agent's skills folder).
name
gjf-flux
description
Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files. USE WHEN needed for generating, refactoring, templating, or scripting Gaussian job files.
compatibility
Requires `uv` installed and available in PATH.
license
LGPL-3.0-or-later
metadata.author
light-cyan
metadata.version
0.1.0
metadata.repository
https://github.com/light-cyan/gjf-flux

gjf-flux (Gaussian Job File Assembly & Extraction)

gjf-flux is a command-line workflow for modular Gaussian .gjf files:

  • Extract a specific section from an existing .gjf (including Link1 multi-step jobs).
  • Assemble directives/route/molecule/appendix blocks into a complete .gjf, or merge multiple tasks into a Link1 job.

When to use

Use this skill when you need to:

  • Reuse parts of Gaussian inputs across many calculations (e.g., route lines, molecule blocks, basis/constraints appendices).
  • Programmatically build .gjf jobs from smaller files (fragments, templates, parameterized directives).
  • Inspect/compare .gjf files by extracting specific sections.

Assumptions / Parsing model (important)

gjf-flux assumes a standard Gaussian input layout:

  • Link1 steps are separated by a blank line, then --Link1--, then a newline.
  • Within each Link1 step, blocks are separated by blank lines.
  • The route section begins at the first line starting with # and continues through subsequent lines.
  • A molecule block is detected when the first line of a block looks like paired integers (e.g., 0 1 or 0 1 0 1 0 1), representing charge/multiplicity pairs.

If a .gjf deviates from these conventions, extraction may fail or misclassify blocks.

Inputs you should request from the user

When helping a user, clarify:

  1. Target action: extract vs assemble.
  2. File paths:
    • Existing .gjf to read, or component files to assemble.
  3. For Link1 jobs:
    • Which step to extract (job_index, 0-based), or how many steps to assemble.
  4. Molecule content:
    • Total charge/multiplicity, fragment charge/multiplicity (if using fragments), coordinate format.
  5. Appendices:
    • Whether there are basis sets, ECPs, ModRedundant constraints, etc.

Core commands (cheat sheet)

1) Extract a section from a .gjf
bash
uvx gjf-flux extract <section_name> <FILE.gjf> [--job_index N]

Where <section_name> is one of:

  • directives
  • route
  • title
  • molecule or molecule-<idx>
  • appendix or appendix-<idx>

Notes:

  • <idx> is 0-based.
  • --job_index selects the Link1 step (0-based, default 0).

Examples:

bash
# Extract the route line from the first Link1 step
uvx gjf-flux extract route input.gjf

# Extract the second molecule block from step 0
uvx gjf-flux extract molecule-1 input.gjf

# Extract the first appendix block from Link1 step 2
uvx gjf-flux extract appendix-0 input.gjf --job_index 2
2) Assemble directives (Link0 commands)
bash
uvx gjf-flux assemble directives --chk FILE --mem SIZE --nprocshared N

This command accepts key/value pairs in the form --key value.

Examples:

bash
uvx gjf-flux assemble directives --chk job.chk --mem 16GB --nprocshared 16

Tip: redirect to a file for later composition:

bash
uvx gjf-flux assemble directives --chk job.chk --mem 16GB --nprocshared 16 > directives.txt
3) Assemble the route section (# line)
bash
uvx gjf-flux assemble route [-l p|n|t|""] <keywords...>

Examples:

bash
#p Opt B3LYP/6-31G(d)
uvx gjf-flux assemble route -l p Opt B3LYP/6-31G(d)

# Use quotes for keywords with parentheses
uvx gjf-flux assemble route -l p "Opt(MaxCycle=100)" "Freq"

Tip:

bash
uvx gjf-flux assemble route -l p "Opt(MaxCycle=100)" "Freq" > route.txt
4) Merge molecule fragments into one molecule block
bash
uvx gjf-flux assemble molecules <frag1.txt> <frag2.txt> ... [--as-fragment] [--charge INT] [--multi INT]

Each fragment file must follow this format:

  • Line 1: charge multiplicity (e.g., 0 1)
  • Following lines: atomic coordinates (Gaussian-style)

Modes:

  • Default: merges into a single molecule block.
  • --as-fragment: assigns Fragment=1,2,... tags and expands the charge/multiplicity header.

Examples:

bash
# Merge two fragments into a single molecule block
uvx gjf-flux assemble molecules fragA.txt fragB.txt > molecule.txt

# Merge as fragments, overriding total charge/multiplicity
uvx gjf-flux assemble molecules fragA.txt fragB.txt --as-fragment --charge 0 --multi 1 > molecule.txt
5) Assemble appendices
bash
uvx gjf-flux assemble appendices <app1.txt> <app2.txt> ...

Examples:

bash
uvx gjf-flux assemble appendices basis.txt modredundant.txt > appendix.txt
6) Assemble a complete single-step .gjf
bash
uvx gjf-flux assemble job \
    --directives directives.txt \
    --route route.txt \
    --title "Your title" \
    --molecule molecule.txt [molecule2.txt ...] \
    [--appendices appendix.txt ...]
7) Merge multiple tasks into a Link1 multi-step job
bash
uvx gjf-flux assemble tasks step1.gjf step2.gjf [step3.gjf ...] > link1.gjf
Show full SKILL.md (272 more words)Show less

End-to-end example (one-liners with command substitution)

This example shows a single-step job assembled from:

  • directives: produced directly from CLI flags
  • route: produced inline from assemble route
  • molecule: extracted from an existing .gjf, then re-merged (optionally overriding multiplicity)
  • appendices: extracted from other .gjf files and concatenated

Note: This uses bash/zsh process substitution (<(...)). If you are on a shell that does not support it, redirect each block into a file first.

bash
# 1) Build directives to a file (recommended; easier to audit)
uvx gjf-flux assemble directives --chk job.chk --mem 16GB --nprocshared 16 > directives.txt

# 2) Assemble a full .gjf using inline-generated route/molecule/appendix blocks
uvx gjf-flux assemble job \
    --directives directives.txt \
    --route <(uvx gjf-flux assemble route -l p "Opt(MaxCycle=100)" "Freq" B3LYP/6-31G(d)) \
    --title "Opt+Freq from extracted building blocks" \
    --molecule <( \
        gjf-flux assemble molecules \
        <(uvx gjf-flux extract molecule-0 reactant.gjf) \
        fragment_extra.xyz \
        --multi 1 \
    ) \
    --appendices \
    <(uvx gjf-flux extract appendix-1 reactant.gjf) \
    <(uvx gjf-flux extract appendix-0 reference.gjf) \
    app_manual.txt \
    > job.gjf

Variants:

  • If you only want to reuse an extracted molecule block verbatim (no merge), pass:
    • --molecule <(uvx gjf-flux extract molecule-0 input.gjf)
  • If you are assembling a Link1 workflow, build each step as its own .gjf and then:
    • uvx gjf-flux assemble tasks step1.gjf step2.gjf > link1.gjf
  1. Create/derive component blocks:
    • directives.txt (from assemble directives or manual)
    • route.txt (from assemble route)
    • molecule.txt (from assemble molecules or extracted from a prior .gjf)
    • appendix.txt (optional)
  2. Assemble a complete job via assemble job.
  3. If you have multiple steps, build each step as a .gjf and then merge using assemble tasks.
  4. Verify by extracting critical sections from the final output.

Common pitfalls

  • Wrong indexing: job_index, molecule-<idx>, and appendix-<idx> are all 0-based.
  • Non-standard .gjf formatting: unusual blank-line structure can break parsing.
  • Fragment files must start with charge multiplicity: otherwise molecule merge will fail.
  • Keyword quoting: route keywords with parentheses should be quoted in the shell.

Notes for agents

  • Prefer asking the user for a concrete example .gjf if parsing fails.
  • When assembling, keep each component file small and purpose-specific; it makes debugging far easier.
  • If the user wants a repeatable pipeline, suggest storing reusable components (route templates, basis set appendices, fragment libraries) in version control.

© 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

Just SKILL.md in quantum-chemistry/gjf-flux of jinzhezenggroup/computational-chemistry-agent-skills.

Open the folder on GitHubat commit 5c19e75

Compare with similar skills

Gjf Flux 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.

Gjf Flux compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gjf Flux this skilljinzhezenggroup/computational-chemistry-agent-skills148—~2kAutomated safety check: PassLGPL-3.0-or-later
Guidelinesakash-network/node1.1k20 repos~577Automated safety check: PassMIT
Migrate Core Code to Submodulestinyhumansai/openhuman42k—~2.6kAutomated safety check: PassGPL-3.0
Component Refactoringlangflow-ai/langflow155k—~3.5kAutomated safety check: PassMIT
Ponytail Lazy Developer ModeDietrichGebert/ponytail160k1 repos~873Automated safety check: PassMIT
ast-grep Structural Searchcode-yeongyu/oh-my-openagent70k—~3.3kAutomated safety check: PassMIT

Similar skills

  • Guidelines

    akash-network/node

    Behavioral guidelines to reduce common LLM coding mistakes. An agent skill from akash-network/node.

    1.1k GitHub starsUsed in 20 repos~577 tokens
    DevelopmentAuto-check passed

  • Migrate Core Code to Submodules

    tinyhumansai/openhuman

    Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.

    42k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed

  • Component Refactoring

    langflow-ai/langflow

    Refactor high-complexity React components in Langflow frontend.

    155k GitHub stars~3.5k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Ponytail Lazy Developer Mode

    DietrichGebert/ponytail

    Makes the agent pick the laziest solution that works: skip unneeded work, reuse what exists, prefer the standard library and platform features, and keep diffs small.

    160k GitHub starsUsed in 1 repo~873 tokens
    DevelopmentAuto-check passed

  • ast-grep Structural Search

    code-yeongyu/oh-my-openagent

    Searches and rewrites code by syntax-tree shape across 25 languages with ast-grep, for codemods, structural queries and YAML lint rules, using a Python wrapper script.

    70k GitHub stars~3.3k tokensUpdated today
    DevelopmentAuto-check passed

  • Systematic Code Refactoring

    luongnv89/claude-howto

    Guides refactoring in phases based on Martin Fowler's method: research, test coverage check, planning and small tested steps, with your approval at each phase.

    42k GitHub stars~3k tokensUpdated today
    DevelopmentAuto-check passed

More from jinzhezenggroup/computational-chemistry-agent-skills

All 62 skills in this repo

  • Quantum ESPRESSO DFT Task Builder

    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.

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

  • 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

Categories

Questions about Gjf Flux

What does Gjf Flux do?

Assemble and extract Gaussian .gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files. Gjf Flux is an agent skill from jinzhezenggroup/computational-chemistry-agent-skills.gjf input file sections (directives, route, title, molecule blocks, appendices) and build single- or multi-step Link1 jobs from modular component files.

When should I use Gjf Flux?

Gjf Flux fits situations like: needed for generating; scripting Gaussian job files.

How do I install Gjf Flux in Claude Code?

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

How do I install Gjf Flux in Codex?

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

Can I use Gjf Flux 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 gjf-flux -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gjf-flux, .gemini/skills/gjf-flux, .github/skills/gjf-flux and .opencode/skills/gjf-flux in your project.

What does Gjf Flux need to run?

Going by SKILL.md and its folder, Gjf Flux needs the command-line tools its instructions call (uvx). Compatibility (from SKILL.md): Requires `uv` installed and available in PATH..

Does Gjf Flux access the network?

SKILL.md contains no URLs. Its commands use uvx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gjf Flux 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 Gjf Flux use?

Gjf Flux 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 Gjf Flux use?

About 2k tokens (SKILL.md is roughly 8.1k 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 Gjf Flux?

Skills that share tags, products or a category with Gjf Flux: Guidelines (akash-network/node, 1.1k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Component Refactoring (langflow-ai/langflow, 155k stars) and Ponytail Lazy Developer Mode (DietrichGebert/ponytail, 160k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gjf Flux?

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.