Agent skill

Chem Neb Barrier

by learningmatter-mit in learningmatter-mit/AtomisticSkills

Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs.

MITAuto-check passed

Install Chem Neb Barrier

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a claude-code

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

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier --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/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/chem-neb-barrier .claude/skills/chem-neb-barrier && 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/

Paste into Claude Code

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .claude/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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

$skill-installer install https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier

Type 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.

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/chem-neb-barrier .agents/skills/chem-neb-barrier && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .agents/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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.

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/chem-neb-barrier .cursor/skills/chem-neb-barrier && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .cursor/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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

$ gemini skills install https://github.com/learningmatter-mit/AtomisticSkills.git --path skills/chem-neb-barrier

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/chem-neb-barrier .gemini/skills/chem-neb-barrier && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .gemini/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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.

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier

Installs 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).

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/chem-neb-barrier .github/skills/chem-neb-barrier && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .github/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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.

skills CLI

$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install learningmatter-mit/AtomisticSkills chem-neb-barrier --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/chem-neb-barrier .opencode/skills/chem-neb-barrier && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "chem-neb-barrier" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-neb-barrier into .opencode/skills/chem-neb-barrier/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-neb-barrier", 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.

Facts

Skill name: chem-neb-barrier
GitHub stars: 176
Token cost: ~1.3k tokens
SKILL.md length: 391 words
Files: 19 (incl. scripts)
Skills in repo: 129
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs.

SKILL.md covers Tools, Model Recommendations, Prerequisites and Examples
Runs Python and Shell scripts from its folder

What it does

Chem Neb Barrier is an agent skill from learningmatter-mit/AtomisticSkills. Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 22 other files, including scripts (for example `examples/LiCoO2/README.md`, `examples/LiCoO2/prepare_licoo2.py` and `examples/LiCoO2/run_example.sh`).

The repository describes itself as: Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc). The licence is MIT.

Example prompts

“/chem-neb-barrier”

Requirements

Python 3
A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit 6257444. 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
Ships 1 file in scripts/ (Python and Shell, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- github.com
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.

Context cost

Chem Neb Barrier loads about 1.3k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 391 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~24
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from learningmatter-mit/AtomisticSkills at commit 6257444, republished under its MIT licence (© learningmatter-mit). 391 words, ~1,265 tokens.

Download SKILL.mdSave it as .claude/skills/chem-neb-barrier/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.

name: chem-neb-barrier
description: Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs.
metadata.category: chemistry, materials
metadata.venv: fairchem, mlip

NEB Barrier Calculation

This skill calculates the activation energy barrier for atomic migration or chemical reaction transition states using the Nudged Elastic Band (NEB) method with Machine Learning Interatomic Potentials (MLIPs).

Supports both:

Materials: solid-state diffusion barriers (periodic systems)
Chemistry: molecular transition states (non-periodic systems)

The script auto-detects periodic boundary conditions from the input structures.

Tools

1. `calculate_barrier.py`

Performs the NEB calculation between two endpoint structures.

Usage:

Use with MACE (periodic materials)

bash

${CLAUDE_SKILL_DIR}/../../venv/run mlip python ${CLAUDE_SKILL_DIR}/scripts/calculate_barrier.py \
    --start_structure <path_to_start.cif> \
    --end_structure <path_to_end.cif> \
    --model_type mace \
    --n_images 5 \
    --fmax 0.05 \
    --output_dir <output_directory>

Use with MACE (non-periodic molecules)

bash

${CLAUDE_SKILL_DIR}/../../venv/run mlip python ${CLAUDE_SKILL_DIR}/scripts/calculate_barrier.py \
    --start_structure reactant.xyz \
    --end_structure product.xyz \
    --model_type mace \
    --model_name MACE-OFF23-small \
    --n_images 7 \
    --fmax 0.05 \
    --output_dir <output_directory>

Use with FairChem

bash

${CLAUDE_SKILL_DIR}/../../venv/run fairchem python ${CLAUDE_SKILL_DIR}/scripts/calculate_barrier.py \
    --start_structure <path_to_start.cif> \
    --end_structure <path_to_end.cif> \
    --model_type fairchem \
    --n_images 5 \
    --fmax 0.05 \
    --output_dir <output_directory>

Use with MatGL

bash

${CLAUDE_SKILL_DIR}/../../venv/run mlip python ${CLAUDE_SKILL_DIR}/scripts/calculate_barrier.py \
    --start_structure <path_to_start.cif> \
    --end_structure <path_to_end.cif> \
    --model_type matgl \
    --n_images 5 \
    --fmax 0.05 \
    --output_dir <output_directory>

Arguments:

--start_structure: Path to the initial stable structure (CIF/POSCAR/XYZ).
--end_structure: Path to the final stable structure (CIF/POSCAR/XYZ).
--model_type: Type of MLIP to use (mace, fairchem, matgl).
--model_name: Specific model name/path (optional, uses default if not specified).
--model_head: Model head for multi-head models (e.g., omat, omol for UMA; omat_pbe, matpes_r2scan for MACE-MH).
--n_images: Number of intermediate images (default: 7).
--fmax: Force convergence criterion in eV/Å (default: 0.02).
--interpolation: Method for initial path generation. Options: linear, idpp (default). Recommended to use idpp for dense systems.
--climb: Use Climbing Image NEB (CI-NEB) (default: True).
--output_dir: Directory to save results and plots.

Outputs:

neb_trajectory.traj: ASE trajectory of the optimized path.
neb_barrier_plot.png: Plot of energy vs reaction coordinate.
neb_results.json: JSON file containing barrier energy and forces.
neb_path.cif (periodic) or neb_path.xyz (non-periodic): Path structures.

Model Recommendations

Show full SKILL.md (178 more words)Show less

Periodic Materials (solid-state diffusion)

Recommended:
- OMAT:
  - MACE-OMAT-0-small
  - MACE-MH-1 (head: omat_pbe)
  - uma-s-1p1 (head: omat)
- MatPES:
  - MACE-MATPES-r2SCAN-0
  - MACE-MH-1 (head: matpes_r2scan)
  - CHGNet-PES-MatPES-r2SCAN-1M-2026.9
  - TensorNet-MatPES-r2SCAN-v2025.1-PES
- These models are trained on datasets including transition states or diverse structures (OMat24, MatPES), making them more reliable for NEB.
Discouraged:
- MPtrj trained models (e.g., M3GNet-MP-2021, CHGNet-MPtrj-2023.12.1-2.7M-PES)
- These are primarily trained on ground-state or near-equilibrium structures and may underestimate barriers or fail to converge for high-energy transition states.

Non-periodic Molecules (transition states)

Recommended:
- MACE-OFF23-small / MACE-OFF23-medium — trained on organic molecules
- uma-s-1p1 (head: omol) — general molecular model
- MACE-MH-1 (head: omol) — multi-head molecular model

Prerequisites

Ensure the appropriate environment is active for the chosen model type (see mcp_config.json).
CRITICAL: The start and end structures MUST be pre-relaxed using the same MLIP model used for the NEB calculation.
- For periodic: Use relax_cell=False (fixed volume) to ensure consistency between endpoints.
- For non-periodic: Ensure pbc=False is set on the structures.
- Use fmax=0.02 eV/Å for tight convergence.
- You can use the relax_structure tool from the corresponding MCP server for this.

Examples

See `examples/` directory for sample inputs and outputs.

Author: Bowen Deng Contact: GitHub @learningmatter-mit

Files

SKILL.md and 18 other files (scripts) in skills/chem-neb-barrier of learningmatter-mit/AtomisticSkills.

SKILL.md
examples/LiCoO2/README.md
examples/LiCoO2/neb_barrier_plot.png
examples/LiCoO2/neb_path.cif
examples/LiCoO2/prepare_licoo2.py
examples/LiCoO2/run_example.sh
examples/butane_conformer/README.md
examples/butane_conformer/anti_butane.xyz
examples/butane_conformer/gauche_butane.xyz
examples/butane_conformer/output/anti_relaxed.xyz
examples/butane_conformer/output/gauche_relaxed.xyz
examples/butane_conformer/output/neb.traj
examples/butane_conformer/output/neb_barrier_plot.png
examples/butane_conformer/output/neb_path.xyz
examples/butane_conformer/output/neb_results.json
examples/butane_conformer/output/ts_neb.xyz
examples/butane_conformer/run_example.py
… and 2 more

Open the folder on GitHubat commit 6257444

Compare with similar skills

Chem Neb Barrier 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.

Chem Neb Barrier compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Chem Neb Barrier this skilllearningmatter-mit/AtomisticSkills	176	—	~1.3k	Automated safety check: Pass	MIT	yesterday
Price Elasticity Calculatorrevfactory/harness-100	1.3k	—	~1.3k	Automated safety check: Pass	Apache-2.0	6 mo ago
Neb Irc Activation Energymajiayu000/claude-skill-registry	666	1 repos	~4k	Automated safety check: Pass	CC-BY-4.0	yesterday
Modeling Activation MetricsPostHog/posthog	40k	—	~1.4k	Automated safety check: Pass	Custom licence	today
Santa Methodaffaan-m/ECC	275k	3 repos	~3.1k	Automated safety check: Pass	MIT	3 days ago
Santa Methodaffaan-m/ECC	275k	—	~2.1k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Price Elasticity Calculator
revfactory/harness-100
A methodology for calculating price elasticity and deriving optimal pricing.
1.3k GitHub stars~1.3k tokensUpdated 6 mo ago
Research & ScienceAuto-check passed
Neb Irc Activation Energy
majiayu000/claude-skill-registry
NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.
666 GitHub starsUsed in 1 repo~4k tokens
Research & ScienceAuto-check passed
Modeling Activation Metrics
PostHog/posthog
Official
Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project.
40k GitHub stars~1.4k tokensUpdated today
Data & AnalyticsAuto-check passed
Santa Method
affaan-m/ECC
Multi-agent adversarial verification: two independent reviewers with the same rubric must both pass before output ships, with a fix-and-re-review convergence loop and human escalation cap.
275k GitHub starsUsed in 3 repos~3.1k tokens
EducationAuto-check passed
Santa Method
affaan-m/ECC
収束ループを持つマルチエージェント敵対的検証。2つの独立したレビューエージェントが両方合格して初めて出力を出荷できます。
275k GitHub stars~2.1k tokensUpdated 3 days ago
Auto-check passed
Santa Method
affaan-m/ECC
具有收敛循环的多智能体对抗验证。两个独立的审查代理必须都通过，输出才能发送。
275k GitHub stars~1.9k tokensUpdated 3 days ago
Auto-check passed

Questions about Chem Neb Barrier

What does Chem Neb Barrier do?

Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs. Chem Neb Barrier is an agent skill from learningmatter-mit/AtomisticSkills. Calculate activation barrier using Nudged Elastic Band (NEB) method with MLIPs.

How do I install Chem Neb Barrier in Claude Code?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a claude-code`. Or copy the skill folder (skills/chem-neb-barrier in learningmatter-mit/AtomisticSkills) into .claude/skills/chem-neb-barrier in your project. Claude Code loads it when a task matches its description.

How do I install Chem Neb Barrier in Codex?

Run `npx skills add learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a codex`. Or copy the skill folder (skills/chem-neb-barrier in learningmatter-mit/AtomisticSkills) into .agents/skills/chem-neb-barrier in your project. Codex loads it when a task matches its description.

Can I use Chem Neb Barrier 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 learningmatter-mit/AtomisticSkills --skill chem-neb-barrier -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chem-neb-barrier, .gemini/skills/chem-neb-barrier, .github/skills/chem-neb-barrier and .opencode/skills/chem-neb-barrier in your project.

What does Chem Neb Barrier need to run?

Going by SKILL.md and its folder, Chem Neb Barrier needs Python and a shell for the scripts in its folder. Our summary lists: Python 3; A Bash shell.

Does Chem Neb Barrier access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Chem Neb Barrier 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Chem Neb Barrier use?

Chem Neb Barrier is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Chem Neb Barrier use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Chem Neb Barrier?

Skills that share tags, products or a category with Chem Neb Barrier: Price Elasticity Calculator (revfactory/harness-100, 1.3k stars), Neb Irc Activation Energy (majiayu000/claude-skill-registry, 666 stars), Modeling Activation Metrics (PostHog/posthog, 40k stars) and Santa Method (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chem Neb Barrier?

learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 176 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 7, 2026.

Source: learningmatter-mit/AtomisticSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Chem Neb Barrier

Facts

At a glance

What it does

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

NEB Barrier Calculation

Tools

1. calculate_barrier.py

Use with MACE (periodic materials)

Use with MACE (non-periodic molecules)

Use with FairChem

Use with MatGL

Model Recommendations

Periodic Materials (solid-state diffusion)

Non-periodic Molecules (transition states)

Prerequisites

Examples

See examples/ directory for sample inputs and outputs.

Files

Compare with similar skills

Similar skills

More from learningmatter-mit/AtomisticSkills

Questions about Chem Neb Barrier

1. `calculate_barrier.py`

See `examples/` directory for sample inputs and outputs.