Agent skill

Phonon

Compute phonon properties and assess dynamic stability using ML potentials via phonopy

Apache-2.0Auto-check passed

Install Phonon

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill phonon -a claude-code

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw phonon --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/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/phonon .claude/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .claude/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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/lamm-mit/scienceclaw/tree/main/skills/phonon

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 lamm-mit/scienceclaw --skill phonon -a codex

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw phonon --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/phonon .agents/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .agents/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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 lamm-mit/scienceclaw --skill phonon -a cursor

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw phonon --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/phonon .cursor/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .cursor/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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/lamm-mit/scienceclaw.git --path skills/phonon

--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 lamm-mit/scienceclaw --skill phonon -a gemini-cli

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw phonon --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/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/phonon .gemini/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .gemini/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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 lamm-mit/scienceclaw phonon

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 lamm-mit/scienceclaw --skill phonon -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/phonon .github/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .github/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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 lamm-mit/scienceclaw --skill phonon -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 lamm-mit/scienceclaw phonon --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/phonon .opencode/skills/phonon && 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 "phonon" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/phonon into .opencode/skills/phonon/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "phonon", 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: phonon
GitHub stars: 244
Token cost: ~871 tokens
SKILL.md length: 309 words
Files: 2 (incl. scripts)
Skills in repo: 85
Repo updated: Aug 21, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Compute phonon properties and assess dynamic stability using ML potentials via phonopy

Works in 8 steps: Load structure from CIF file → Create phonopy object with appropriate… → Generate symmetry-inequivalent displaced… → …
SKILL.md covers Prerequisites, Scripts, Parameters and Output (JSON), plus 2 more sections
Runs Python scripts from its folder; calls python3 and pip

What it does

Phonon is an agent skill from lamm-mit/scienceclaw. Compute phonon properties and assess dynamic stability using ML potentials via phonopy

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/phonon_stability.py`).

The licence is Apache-2.0.

Example prompts

“/phonon”

Requirements

Python 3

Workflow steps

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

Load structure from CIF file
Create phonopy object with appropriate supercell
Generate symmetry-inequivalent displaced supercells (finite displacement method)
Compute forces on each displaced supercell using UMA
Build force constant matrix, apply symmetry and acoustic sum rule
Compute phonon frequencies at commensurate q-points
Check for imaginary modes → determine stability
Optionally compute thermal properties (free energy, entropy, heat capacity)

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. 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), which the agent can run.
Shell commands in SKILL.md call:
- python3
- pip
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):
- phonopy.github.io
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

Phonon loads about 871 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 309 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~23
When it runs · the whole SKILL.md, loaded when a task matches: ~871

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 lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 309 words, ~871 tokens.

Download SKILL.mdSave it as .claude/skills/phonon/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: phonon
description: Compute phonon properties and assess dynamic stability using ML potentials via phonopy

Phonon Skill

Compute phonon properties (frequencies, DOS, thermal properties) and assess dynamic stability of crystal structures using the finite-displacement method via phonopy with forces from ML interatomic potentials (UMA/fairchem).

A structure is dynamically stable if all phonon frequencies are real (no imaginary modes). Imaginary frequencies indicate the structure is at a saddle point on the potential energy surface and would spontaneously distort.

Prerequisites

phonopy installed (pip install phonopy)
fairchem-core installed (for UMA calculator)
ase installed
GPU recommended for UMA force calculations

Scripts

`phonon_stability.py` — Check dynamic stability of crystal structures

From a directory of CIF files:

bash

python3 {baseDir}/scripts/phonon_stability.py \
  --structures-dir ./relaxed_structures \
  --format json

From a single CIF file:

bash

python3 {baseDir}/scripts/phonon_stability.py \
  --structure relaxed_LaH10.cif \
  --format json

With custom supercell size:

bash

python3 {baseDir}/scripts/phonon_stability.py \
  --structures-dir ./candidates \
  --supercell 2,2,2 \
  --model uma-s-1p2 \
  --format json

Parameters

Parameter	Description
`--structure`	Path to a single CIF/POSCAR file
`--structures-dir`	Directory of CIF files to analyze
`--after-job`	SLURM job ID to wait for before starting (e.g. wait for UMA screening to finish)
`--supercell`	Supercell dimensions (default: auto, typically 2,2,2)
`--displacement`	Finite displacement distance in Angstrom (default: 0.01)
`--model`	UMA checkpoint (default: `uma-m-1p1`)
`--task`	UMA task (default: `omat`)
`--device`	`cuda` (default) or `cpu`
`--imaginary-threshold`	Frequency threshold in THz for instability (default: -0.5)
`--output-dir`	Directory for output files
`--format`	`summary` \| `json`

Output (JSON)

json

{
  "status": "COMPLETED",
  "results": [
    {
      "label": "LaH10_relaxed",
      "formula": "LaH10",
      "dynamically_stable": true,
      "min_frequency_THz": 0.23,
      "max_frequency_THz": 45.2,
      "n_imaginary_modes": 0,
      "n_modes": 33,
      "thermal_properties": {
        "300K": {
          "free_energy_kJ_per_mol": -12.5,
          "entropy_J_per_mol_K": 45.2,
          "heat_capacity_J_per_mol_K": 38.1
        }
      }
    }
  ]
}

Dynamic Stability Criteria

A structure is flagged as dynamically unstable if:

Any phonon frequency at the Gamma point is below the imaginary threshold (default: -0.5 THz)
Any phonon frequency at non-Gamma q-points is below 0 THz

Small negative frequencies near Gamma (> -0.5 THz) are typically numerical artifacts from the acoustic sum rule and are ignored.

How It Works

Load structure from CIF file
Create phonopy object with appropriate supercell
Generate symmetry-inequivalent displaced supercells (finite displacement method)
Compute forces on each displaced supercell using UMA
Build force constant matrix, apply symmetry and acoustic sum rule
Compute phonon frequencies at commensurate q-points
Check for imaginary modes → determine stability
Optionally compute thermal properties (free energy, entropy, heat capacity)

Files

SKILL.md and 1 other file (scripts) in skills/phonon of lamm-mit/scienceclaw.

SKILL.md
scripts/phonon_stability.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Phonon 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.

Phonon compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Phonon this skilllamm-mit/scienceclaw	244	—	~871	Automated safety check: Pass	Apache-2.0	1 mo ago
Ito Computeaffaan-m/ECC	275k	1 repos	~1.7k	Automated safety check: Pass	MIT	3 days ago
CSS At Propertythedaviddias/Front-End-Checklist	74k	—	~602	Automated safety check: Pass	MIT	yesterday
Senior Computer Visiondavila7/claude-code-templates	32k	3 repos	~1.4k	Automated safety check: Pass	MIT	today
Dynamic Workflow Modeaffaan-m/ECC	275k	1 repos	~1.3k	Automated safety check: Pass	MIT	3 days ago
Senior Computer Visionalirezarezvani/claude-skills	28k	2 repos	~3.2k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Ito Compute
affaan-m/ECC
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately…
275k GitHub starsUsed in 1 repo~1.7k tokens
Business, Finance & HRAuto-check passed
CSS At Property
thedaviddias/Front-End-Checklist
A skill your agent uses when implementing animated gradients, complex CSS transitions that involve custom property values, or building a typed design token system where custom property misuse should…
74k GitHub stars~602 tokensUpdated yesterday
Frontend & DesignAuto-check passed
Senior Computer Vision
davila7/claude-code-templates
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems.
32k GitHub starsUsed in 3 repos~1.4k tokens
AI & LLM EngineeringAuto-check passed
Dynamic Workflow Mode
affaan-m/ECC
Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
275k GitHub starsUsed in 1 repo~1.3k tokens
Auto-check passed
Senior Computer Vision
alirezarezvani/claude-skills
Computer vision engineering skill for object detection, image segmentation, and visual AI systems.
28k GitHub starsUsed in 2 repos~3.2k tokens
AI & LLM EngineeringAuto-check passed
Logical Properties
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use CSS logical properties for i18n and RTL support.
74k GitHub stars~526 tokensUpdated yesterday
Frontend & DesignAuto-check passed

Questions about Phonon

What does Phonon do?

Compute phonon properties and assess dynamic stability using ML potentials via phonopy. Phonon is an agent skill from lamm-mit/scienceclaw.

How do I install Phonon in Claude Code?

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

How do I install Phonon in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill phonon -a codex`. Or copy the skill folder (skills/phonon in lamm-mit/scienceclaw) into .agents/skills/phonon in your project. Codex loads it when a task matches its description.

Can I use Phonon 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 lamm-mit/scienceclaw --skill phonon -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/phonon, .gemini/skills/phonon, .github/skills/phonon and .opencode/skills/phonon in your project.

What does Phonon need to run?

Going by SKILL.md and its folder, Phonon needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3.

Does Phonon access the network?

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

Is Phonon 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 Phonon use?

Phonon is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Phonon use?

About 871 tokens (SKILL.md is roughly 3.5k 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 Phonon?

Skills that share tags, products or a category with Phonon: Ito Compute (affaan-m/ECC, 275k stars), CSS At Property (thedaviddias/Front-End-Checklist, 74k stars), Senior Computer Vision (davila7/claude-code-templates, 32k stars) and Dynamic Workflow Mode (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 Phonon?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 21, 2026.

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

Install Phonon

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Phonon Skill

Prerequisites

Scripts

phonon_stability.py — Check dynamic stability of crystal structures

Parameters

Output (JSON)

Dynamic Stability Criteria

How It Works

Files

Compare with similar skills

Similar skills

More from lamm-mit/scienceclaw

Questions about Phonon

`phonon_stability.py` — Check dynamic stability of crystal structures