Astropy
zLanqing/codex-claude-academic-skills
Comprehensive Python library for astronomy and astrophysics.
Agent skill
by jinzhezenggroup in 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.
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxff --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .claude/skills/lammps-reaxff && rm -rf skills-srcUse ~/.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/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .claude/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxffType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxff --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .agents/skills/lammps-reaxff && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .agents/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxff --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .cursor/skills/lammps-reaxff && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .cursor/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git --path molecular-dynamics/lammps-reaxff--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxff --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .gemini/skills/lammps-reaxff && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .gemini/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxffInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .github/skills/lammps-reaxff && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .github/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jinzhezenggroup/computational-chemistry-agent-skills lammps-reaxff --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jinzhezenggroup/computational-chemistry-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/molecular-dynamics/lammps-reaxff .opencode/skills/lammps-reaxff && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lammps-reaxff" agent skill from https://github.com/jinzhezenggroup/computational-chemistry-agent-skills/tree/master/molecular-dynamics/lammps-reaxff into .opencode/skills/lammps-reaxff/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lammps-reaxff", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
lammps-reaxffPrepares and explains LAMMPS input scripts for reactive molecular dynamics with the ReaxFF potential, including charge equilibration and ensemble choice.
The agent first confirms three inputs before writing anything: the ReaxFF force field file (an `ffield.reax.*` file), the structure data file, and the mapping from LAMMPS atom types to elements used in `pair_coeff`. It then writes an annotated `input.lammps` with `pair_style reaxff`, a charge-capable atom style and a single `fix qeq/reaxff`. It warns against using `fix property/atom q` as a stand-in for real charges.
It asks only for what is still missing: the ensemble (NVE, NVT or NPT), temperature, pressure for NPT, timestep, run length, and how LAMMPS should be launched. With internet access and `uv` it can run `uvx --from 'lammps[mpi]' lmp -in input.lammps`; on an HPC system it asks which executable and MPI command you use instead of inventing one. A workflow reference and an NVT template ship with it, and species analysis is among the diagnostics it can add.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 5c19e75. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
uvxFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.lammps.orggithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires a LAMMPS build with the REAXFF package enabled (pair_style reaxff and fix qeq/reaxff). Optional acceleration variants: reaxff/omp or reaxff/kk.
From compatibility in the SKILL.md frontmatter.
LAMMPS ReaxFF Setup 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 105 tokens; SKILL.md has 659 words of instructions outside code blocks.
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.
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.
The full file from jinzhezenggroup/computational-chemistry-agent-skills at commit 5c19e75, republished under its LGPL-3.0-or-later licence (© jinzhezenggroup). 659 words, ~1,814 tokens.
.claude/skills/lammps-reaxff/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Use this skill when the user wants to run molecular dynamics in LAMMPS with a ReaxFF force field, prepare or explain an input.lammps file, and set up charge equilibration (QEq) correctly.
ffield.reax.*). Do not guess which file is appropriate.potentials/ffield.reax.* at https://github.com/lammps/lammps/tree/develop/potentials).data.system) and the atom type → element mapping needed by pair_coeff.atom_style charge or atom_style full, and ensure charges are initialized either from the data file (with a charge column compatible with the chosen atom_style) or via explicit commands (e.g. set or equal-style variables). Do not rely on fix property/atom q as a substitute for a real charge field used by ReaxFF/QEq.fix qeq/reaxff, unless the user explicitly requests otherwise.lmp -h output before execution.Ask only for what is missing:
ffield.reax...)pair_coeff * * ffield ...)uv is available)Use:
uvx --from 'lammps[mpi]' lmp -in input.lammpsNotes:
error while loading shared libraries: libmpi.so..., you likely installed an MPI-linked lmp without MPI runtime libraries. Prefer uvx --from 'lammps[mpi]' ... (bundles MPI runtime), or load/install MPICH/OpenMPI via system packages/conda/HPC module.Do not invent the executable. Ask which command should be used, e.g.:
lmp -in input.lammpsmpirun -np 32 lmp_mpi -in input.lammpssrun lmp -in input.lammpsSee also assets/input.reaxff.nvt.lammps.
# --------- user knobs ---------
variable NSTEPS equal 200000
variable THERMO equal 200
variable DUMP equal 1000
variable TEMP equal 300.0
variable TAU_T equal 100.0
# Timestep (fs for units real). For high-T / reactive runs, 0.1 fs is often safer.
variable DT equal 0.25
# QEq parameters
variable QEQ_EVERY equal 1
variable QEQ_TOL equal 1.0e-6
variable QEQ_CUTLO equal 0.0
variable QEQ_CUTHI equal 10.0
units real
boundary p p p
atom_style charge
read_data data.system
neighbor 2.0 bin
neigh_modify every 1 delay 0 check yes
# ReaxFF potential
pair_style reaxff NULL
pair_coeff * * ffield.reax C H O
# Charge equilibration (required for most ReaxFF parameterizations)
fix fqeq all qeq/reaxff ${QEQ_EVERY} ${QEQ_CUTLO} ${QEQ_CUTHI} ${QEQ_TOL} reaxff
# (`reaxff` here means QEq parameters are extracted from the ReaxFF force field file.)
# Thermo and trajectory
thermo_style custom step temp pe ke etotal press vol density
thermo ${THERMO}
dump 1 all custom ${DUMP} traj.lammpstrj id type q x y z
# Dynamics
velocity all create ${TEMP} 12345 mom yes rot yes dist gaussian
fix fnvt all nvt temp ${TEMP} ${TEMP} ${TAU_T}
timestep ${DT}
run ${NSTEPS}units real is a common choice for ReaxFF (time in fs). Many published ReaxFF workflows use real, but the correct choice depends on the parameterization and your conventions.0.25 fs may be fine for moderate temperatures, but for high-temperature ReaxFF (especially with H present) it is common to reduce to 0.1 fs (or even 0.05 fs if needed). A quick sanity check is a short NVE segment to verify total-energy drift before running long NVT/NPT.atom_style charge is used because ReaxFF and QEq require per-atom charges.pair_style reaxff NULL uses default ReaxFF control settings. If you have a ReaxFF control file, replace NULL with its filename.pair_coeff * * ffield.reax C H O:fix qeq/reaxff ... reaxff uses QEq parameters extracted from the ReaxFF force field file.etotal drift is reasonable (and that the run does not blow up).Example (units real):
reset_timestep 0
unfix fnvt
fix fnve all nve
# high-T ReaxFF often needs a smaller timestep
# (common choices: 0.1 fs; if needed 0.05 fs)
timestep 0.1
run 2000maxiter (see LAMMPS fix qeq/reaxff).If the user wants reaction product tracking, add fix reaxff/species (see references/reaxff-workflow.md). This writes time series counts of detected molecular species using bond-order cutoffs.
After a run, report at least:
log.lammps)© 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
SKILL.md and 2 other files (references, assets) in molecular-dynamics/lammps-reaxff of jinzhezenggroup/computational-chemistry-agent-skills.
Open the folder on GitHubat commit 5c19e75
LAMMPS ReaxFF Setup 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LAMMPS ReaxFF Setup this skilljinzhezenggroup/computational-chemistry-agent-skills | 148 | — | ~1.8k | Automated safety check: Pass | LGPL-3.0-or-later | |
| AstropyzLanqing/codex-claude-academic-skills | 4.7k | 13 repos | ~2.9k | Automated safety check: Pass | BSD-3-Clause | |
| PymatgenzLanqing/codex-claude-academic-skills | 4.7k | 11 repos | ~5k | Automated safety check: Pass | MIT | |
| Cantera Ignition DelayK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Weathertrpc-group/trpc-agent-go | 1.9k | 8 repos | ~591 | Automated safety check: Pass | Apache-2.0 | |
| Pymol VisualizationChatMol/ChatMol | 373 | — | ~1.2k | Automated safety check: Pass | MIT |
zLanqing/codex-claude-academic-skills
Comprehensive Python library for astronomy and astrophysics.
zLanqing/codex-claude-academic-skills
Materials science toolkit. An agent skill from zLanqing/codex-claude-academic-skills.
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.
trpc-group/trpc-agent-go
Get current weather and forecasts via wttr.in or Open-Meteo.
ChatMol/ChatMol
Generate publication-quality molecular visualization images using PyMOL.
Muuuun/luxas
Write domain-authentic review articles that synthesize rather than stack.
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.
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.
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.
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.
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.
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…
Categories
Prepares and explains LAMMPS input scripts for reactive molecular dynamics with the ReaxFF potential, including charge equilibration and ensemble choice. *` file), the structure data file, and the mapping from LAMMPS atom types to elements used in `pair_coeff`.lammps` with `pair_style reaxff`, a charge-capable atom style and a single `fix qeq/reaxff`.
LAMMPS ReaxFF Setup fits situations like: setting up a reactive molecular dynamics run with a ReaxFF force field; getting a working, commented input.lammps template for a new system; fixing charge equilibration or atom type mapping in an existing ReaxFF input; adding species analysis to a ReaxFF simulation.
Run `npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a claude-code`. Or copy the skill folder (molecular-dynamics/lammps-reaxff in jinzhezenggroup/computational-chemistry-agent-skills) into .claude/skills/lammps-reaxff in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jinzhezenggroup/computational-chemistry-agent-skills --skill lammps-reaxff -a codex`. Or copy the skill folder (molecular-dynamics/lammps-reaxff in jinzhezenggroup/computational-chemistry-agent-skills) into .agents/skills/lammps-reaxff in your project. Codex loads it when a task matches its description.
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 lammps-reaxff -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lammps-reaxff, .gemini/skills/lammps-reaxff, .github/skills/lammps-reaxff and .opencode/skills/lammps-reaxff in your project.
Going by SKILL.md and its folder, LAMMPS ReaxFF Setup needs the command-line tools its instructions call (uvx). Our summary lists: A LAMMPS build with the REAXFF package enabled; A ReaxFF force field file such as `ffield.reax.*`; `uv` and internet access for the online run mode. Compatibility (from SKILL.md): Requires a LAMMPS build with the REAXFF package enabled (pair_style reaxff and fix qeq/reaxff). Optional acceleration variants: reaxff/omp or reaxff/kk..
SKILL.md names 2 domains. As links in the text: docs.lammps.org and github.com. This is read from the text; nothing was executed.
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.
LAMMPS ReaxFF Setup 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.
About 1.8k tokens (SKILL.md is roughly 7.3k 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 440 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with LAMMPS ReaxFF Setup: 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.
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.