Install the "mat-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .claude/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "mat-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .agents/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "mat-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .cursor/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "mat-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .gemini/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "mat-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .github/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster -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-dft-lobster" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/mat-dft-lobster into .opencode/skills/mat-dft-lobster/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mat-dft-lobster", 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-dft-lobster
GitHub stars
175
Token cost
~1.2k tokens
SKILL.md length
535 words
Files
5 (incl. scripts)
Skills in repo
129
Repo updated
First seen
Licence
MIT
At a glance
Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS).
Works in 2 steps: Generate and Execute the Workflow → Parse and Analyze Output
SKILL.md covers Goal, Background, Installation and Instructions, plus 2 more sections
Runs Python scripts from its folder
What it does
Mat Dft Lobster is an agent skill from learningmatter-mit/AtomisticSkills. Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS).
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `examples/GaAs/README.md`, `examples/GaAs/gaas_flow.json` and `scripts/analyze_lobster.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-dft-lobster”
Requirements
Python 3
Workflow steps
2 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 2 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):
cohp.de
doi.org
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 Dft Lobster loads about 1.2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 535 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~42
When it runs· the whole SKILL.md, loaded when a task matches
~1.2k
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); the scripts in this folder are not scanned.
Download SKILL.mdSave it as .claude/skills/mat-dft-lobster/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
mat-dft-lobster
description
Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS).
metadata.category
materials
metadata.venv
cpu
mat-dft-lobster
<!-- mcp-tools-note -->
[!NOTE]
Steps written server.tool are MCP tool calls: atomate2.run_atomate2_vasp_calculation is the run_atomate2_vasp_calculation
tool of the atomate2 server (mcp__atomate2__run_atomate2_vasp_calculation, or
mcp__plugin_atomistic-skills_atomate2__run_atomate2_vasp_calculation 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 atomate2 run_atomate2_vasp_calculation key=value
Goal
To calculate advanced chemical bonding properties—like Crystal Orbital Hamilton Populations (COHP), atomic charges, projected DOS, and bonding integrands (ICOHP)—by projecting converged plane-wave Density Functional Theory (DFT) wavefunctions onto a localized, atomic-like basis set using the LOBSTER code.
Background
Standard plane-wave DFT (e.g., VASP) distributes electron density uniformly across reciprocal space, which is computationally robust but lacks explicit chemical intuition regarding localized bonds. LOBSTER (Local Orbital Basis Suite Towards Electronic-Structure Reconstruction) takes the massive WAVECAR from VASP and projects it back to an atomic orbital basis to recover classical chemical bonding insights.
Because WAVECAR files are extremely large (often tens or hundreds of gigabytes), LOBSTER analysis must be performed on the same remote node directly after the VASP static loop. The atomate2VaspLobsterMaker automates this sequentially (Relax -> Static -> Lobster) and ensures the massive WAVECAR is deleted once the projection completes.
Installation
LOBSTER is free to download for non-commercial use from http://www.cohp.de/.
To use this skill, deploy the compiled lobster binary to your remote HPC worker or local testing environment and ensure its path is exported in your environment PATH. All required Python packages (lobsterpy, ijson) are already provided by the cpu environment.
Instructions
1. Generate and Execute the Workflow
To submit a LOBSTER workflow, utilize the built-in MCP tool. This natively maps the VaspLobsterMaker directed acyclic graph (DAG) to your HPC resources:
execution_mode: "remote" (to execute on the HPC worker)
CRITICAL: Do not run this locally unless you are purely generating testing DAGs (check_only=True). The generated flow contains heavy VASP iterations and high-memory LOBSTER matrix projections.
Show full SKILL.md (205 more words)Show less
2. Parse and Analyze Output
Once completed, the termination node returns a LobsterTaskDocument. The most critical file generated is COHPCAR.lobster, which contains the Crystal Orbital Hamilton Populations (COHP).
To analyze COHP outputs, the standard package is LobsterPy. It offers both CLI and Python API tools:
Via CLI:
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu lobsterpy automatic-plot
Via Python API:
Use the provided analyze_lobster.py script as a baseline to parse and visualize the COHPCAR out of the compute node limits.
You can test the DAG generation by running the MCP tool with check_only=True on a structure, or if testing scripts manually:
bash
cd ${CLAUDE_SKILL_DIR}/examples/GaAs
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ../../scripts/generate_inputs.py --output gaas_flow.json
To plot a sample COHPCAR:
bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/analyze_lobster.py --cohpcar COHPCAR.lobster --poscar POSCAR --save cohp_plot.png
Constraints
Environments: Scripts require the cpu environment.
HPC Execution: You must map this flow to run on an HPC environment natively since WAVECAR sizes exceed optimal transfer limits. Ensure both vasp_std and lobster binaries are available to the workers.
Basis Sets: The VaspLobsterMaker optimally restricts VASP settings (e.g., setting ISYM=-1, generating all $k$-points explicitly) to comply with LOBSTER's mathematical constraints. Do not manually override these strict geometry settings unless required by standard pseudopotential edge cases.
References
Maintz, S., Deringer, V. L., Tchougréeff, A. L., & Dronskowski, R. "LOBSTER: A tool to extract chemical bonding from plane-wave based DFT", J. Comput. Chem., 37, 1030-1035 (2016). DOI
Mat Dft Lobster 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 Dft Lobster compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Mat Dft Lobster 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.
Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS). Mat Dft Lobster is an agent skill from learningmatter-mit/AtomisticSkills. Construct computational flows for VASP electronic structure projection via LOBSTER to calculate chemical bonding insights (COHP, atomic charges, DOS).
How do I install Mat Dft Lobster in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill mat-dft-lobster -a claude-code`. Or copy the skill folder (skills/mat-dft-lobster in learningmatter-mit/AtomisticSkills) into .claude/skills/mat-dft-lobster in your project. Claude Code loads it when a task matches its description.
How do I install Mat Dft Lobster in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill mat-dft-lobster -a codex`. Or copy the skill folder (skills/mat-dft-lobster in learningmatter-mit/AtomisticSkills) into .agents/skills/mat-dft-lobster in your project. Codex loads it when a task matches its description.
Can I use Mat Dft Lobster 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-dft-lobster -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-dft-lobster, .gemini/skills/mat-dft-lobster, .github/skills/mat-dft-lobster and .opencode/skills/mat-dft-lobster in your project.
What does Mat Dft Lobster need to run?
Going by SKILL.md and its folder, Mat Dft Lobster needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Mat Dft Lobster access the network?
SKILL.md names 3 domains. As links in the text: cohp.de, doi.org and github.com. This is read from the text; nothing was executed.
Is Mat Dft Lobster 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 Dft Lobster use?
Mat Dft Lobster 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 Dft Lobster use?
About 1.2k tokens (SKILL.md is roughly 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 Mat Dft Lobster?
Skills that share tags, products or a category with Mat Dft Lobster: 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 Dft Lobster?
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.
