Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .claude/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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.
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 mat-electronic-structure -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .agents/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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 mat-electronic-structure -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .cursor/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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.
--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 mat-electronic-structure -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .gemini/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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.
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 mat-electronic-structure -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .github/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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 mat-electronic-structure -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "mat-electronic-structure" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-electronic-structure into .opencode/skills/mat-electronic-structure/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-electronic-structure", 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
mat-electronic-structure
GitHub stars
175
Token cost
~2.1k tokens
SKILL.md length
601 words
Files
7 (incl. scripts)
Skills in repo
129
Repo updated
First seen
Licence
MIT
At a glance
Calculate electronic band structure and density of states using atomate2 and VASP.
Works in 3 steps: Obtain or Prepare the Input Structure → Run Band Structure Calculation → Post-Process and Visualize Results
SKILL.md covers Goal, Instructions, Examples and Constraints, plus 1 more section
Runs Python scripts from its folder
What it does
Mat Electronic Structure is an agent skill from learningmatter-mit/AtomisticSkills. Calculate electronic band structure and density of states using atomate2 and VASP.
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts (for example `examples/README.md`, `scripts/get_mp_electronic_structure.py` and `scripts/plot_band_structure.py`).
It works with Model Context Protocol. 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
“/mat-electronic-structure”
Requirements
Python 3
Workflow steps
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 7f2d86d. 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 3 files in scripts/ (Python), 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
Mat Electronic Structure loads about 2.1k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 601 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~27
When it runs· the whole SKILL.md, loaded when a task matches
~2.1k
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); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/mat-electronic-structure/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
mat-electronic-structure
description
Calculate electronic band structure and density of states using atomate2 and VASP.
metadata.category
materials
metadata.venv
cpu
Electronic Structure
<!-- mcp-tools-note -->
[!NOTE]
Steps written server.tool are MCP tool calls: base.search_materials_project_by_formula is the search_materials_project_by_formula
tool of the base server (mcp__base__search_materials_project_by_formula, or
mcp__plugin_atomistic-skills_base__search_materials_project_by_formula when installed as a plugin).
Without a connected server, run the same tools from the shell. Tools named in
one command share a process, so a model loaded by load_model stays loaded:
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python -m src.mcp_server.cli base search_materials_project_by_formula key=value
${CLAUDE_SKILL_DIR}/../../venv/run cpu python -m src.mcp_server.cli atomate2 run_atomate2_vasp_calculation key=value
Goal
To calculate the electronic band structure of a crystalline material, revealing the energy-momentum relationship for electrons and determining whether the material is metallic, semiconducting, or insulating. This includes computing the band gap ($E_g$), identifying direct vs. indirect transitions, and visualizing the dispersion along high-symmetry k-paths.
Instructions
1. Obtain or Prepare the Input Structure
Start with a relaxed crystalline structure in CIF or POSCAR format. You can:
Pre-computed band structure along high-symmetry paths
Density of states (DOS)
Band gap (energy, direct/indirect)
Fermi energy
When to use MP retrieval vs. calculations:
Retrieve from MP: Quick screening, validation, known materials
Run calculations: New materials, custom structures, specific DFT settings
3. Post-Process and Visualize Results
After the calculation completes, parse the results and generate a band structure plot:
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/plot_band_structure.py \
band_structure_results \
--output band_structure.png
The script will:
Parse the vasprun.xml.gz from the non-SCF job
Extract band gap information (energy, directness, transition)
Generate a publication-quality band structure plot
For DOS (uniform mode):
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/plot_dos.py \
dos_results \
--output dos.png
The script will:
Parse the vasprun.xml.gz from the uniform k-mesh job
Extract band gap and Fermi level
Generate a DOS plot
Alternative: Manual post-processing with pymatgen
python
from pymatgen.io.vasp import BSVasprun
from pymatgen.electronic_structure.plotter import BSPlotter
# Load band structure from atomate2 results
vasprun_path = "band_structure_results/results/structure_0/job_*/vasprun.xml.gz"
vasprun = BSVasprun(vasprun_path, parse_projected_eigen=False)
bs = vasprun.get_band_structure(line_mode=True)
# Get band gap
if not bs.is_metal():
bg = bs.get_band_gap()
print(f"Band gap: {bg['energy']:.3f} eV")
print(f"Direct: {bg['direct']}")
print(f"Transition: {bg['transition']}")
# Plot
plotter = BSPlotter(bs)
ax = plotter.get_plot(ylim=(-10, 10))
ax.get_figure().savefig("band_structure.png", dpi=300, bbox_inches='tight')
Examples
Show full SKILL.md (241 more words)Show less
Silicon Band Structure Calculation
python
# 1. Search for Si structure
base.search_materials_project_by_formula(
formula="Si",
save_to_file="Si.cif"
)
# 2. Run band structure calculation
atomate2.run_atomate2_vasp_calculation(
structures_path="Si.cif",
output_dir="./Si_bands",
calculation_type="band_structure",
bandstructure_mode="line",
preset_type="omat",
execution_mode="local"
)
# 3. Plot results
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/plot_band_structure.py Si_bands --output Si_bands.png
See examples/ for a complete Si band structure calculation showing an indirect band gap of 0.581 eV.
Silicon Density of States (DOS)
python
# 1. Use existing Si structure (or search Materials Project)
# 2. Run DOS calculation with uniform k-mesh
atomate2.run_atomate2_vasp_calculation(
structures_path="Si.cif",
output_dir="./Si_dos",
calculation_type="band_structure",
bandstructure_mode="uniform", # Uniform k-mesh for DOS
preset_type="omat",
execution_mode="local"
)
# 3. Plot DOS
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/plot_dos.py Si_dos --output Si_dos.png
See examples/ for the complete DOS calculation showing the distribution of electronic states.
Constraints
Structure Requirements: Input must be a crystalline structure with well-defined symmetry. Band structure calculations are not meaningful for amorphous or highly disordered materials.
PMG_VASP_PSP_DIR must point to POTCAR directory (or set in ~/.pmgrc.yaml)
For remote execution: Atomate2/jobflow-remote must be configured
Environments:
Band structure calculation: cpu (via MCP tool)
Post-processing scripts: cpu (pymatgen, matplotlib)
Functional Choice:
PBE (omat, mp presets) typically underestimates band gaps
For accurate gaps: Use hybrid functionals (HSE06) or GW methods (not yet supported)
MatPES presets (matpes-pbe, matpes-r2scan) use r2SCAN which improves gap predictions
k-point Density: The automatic k-path generation uses pymatgen's HighSymmKpath. For very accurate results, you may need to manually specify denser k-paths.
Spin-Polarization: Current implementation assumes non-spin-polarized calculations. For magnetic materials, additional configuration may be needed.
Foundation Potential Recommendations
For exploratory band structure analysis using MLIPs (not DFT):
CHGNet: Can predict band gaps, but accuracy varies
Note: MACE, M3GNet, and other MLIPs trained on PES data do not predict electronic properties
For production calculations, always use DFT (this skill) and choose the appropriate functional:
Standard screening: PBE (omat/mp presets)
Improved gaps: r2SCAN (matpes-r2scan preset)
Accurate gaps: HSE06 or GW (requires custom INCAR settings)
Mat Electronic Structure 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.
Mat Electronic Structure compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Mat Electronic Structure this skilllearningmatter-mit/AtomisticSkills
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
Define a docking search box (center coordinates + box dimensions in Angstroms) from a co-crystal ligand, binding-site residues, or a saved JSON specification.
Calculate electronic band structure and density of states using atomate2 and VASP. Mat Electronic Structure is an agent skill from learningmatter-mit/AtomisticSkills. Calculate electronic band structure and density of states using atomate2 and VASP.
How do I install Mat Electronic Structure in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill mat-electronic-structure -a claude-code`. Or copy the skill folder (skills/mat-electronic-structure in learningmatter-mit/AtomisticSkills) into .claude/skills/mat-electronic-structure in your project. Claude Code loads it when a task matches its description.
How do I install Mat Electronic Structure in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill mat-electronic-structure -a codex`. Or copy the skill folder (skills/mat-electronic-structure in learningmatter-mit/AtomisticSkills) into .agents/skills/mat-electronic-structure in your project. Codex loads it when a task matches its description.
Can I use Mat Electronic Structure 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 mat-electronic-structure -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mat-electronic-structure, .gemini/skills/mat-electronic-structure, .github/skills/mat-electronic-structure and .opencode/skills/mat-electronic-structure in your project.
What does Mat Electronic Structure need to run?
Going by SKILL.md and its folder, Mat Electronic Structure needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Mat Electronic Structure 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 Mat Electronic Structure 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 Mat Electronic Structure use?
Mat Electronic Structure 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 Mat Electronic Structure use?
About 2.1k tokens (SKILL.md is roughly 8.3k 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 Mat Electronic Structure?
Skills that share tags, products or a category with Mat Electronic Structure: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Mat Electronic Structure?
learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 175 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 6, 2026.
