New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Mat Dft Mixing Functionals

by learningmatter-mit in learningmatter-mit/AtomisticSkills

Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations.

MITAuto-check passed

Install Mat Dft Mixing Functionals

skills CLI
$ npx skills add learningmatter-mit/AtomisticSkills --skill mat-dft-mixing-functionals -a claude-code

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

GitHub CLI
$ gh skill install learningmatter-mit/AtomisticSkills mat-dft-mixing-functionals --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/mat-dft-mixing-functionals .claude/skills/mat-dft-mixing-functionals && 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/

Facts

Skill name
mat-dft-mixing-functionals
GitHub stars
175
Token cost
~1k tokens
SKILL.md length
393 words
Files
4 (incl. scripts)
Skills in repo
129
Repo updated
First seen
Licence
MIT

At a glance

Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations.

  • Works in 3 steps: Check Compatibility → Apply Correction to a Structure → Batch Processing
  • SKILL.md covers Goal, Scientific Context, Compatible Models and Instructions, plus 1 more section
  • Runs Python scripts from its folder

What it does

Mat Dft Mixing Functionals is an agent skill from learningmatter-mit/AtomisticSkills. Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `resources/gga-ggau-mixed-mlips.yaml`, `scripts/apply_correction.py` and `scripts/check_compatibility.py`).

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-mixing-functionals”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Check Compatibility
  2. Apply Correction to a Structure
  3. Batch Processing

What it can do on your machine

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):

    • pymatgen.org
    • doi.org
    • arxiv.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 Mixing Functionals loads about 1k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 393 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~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.

SKILL.md

The full file from learningmatter-mit/AtomisticSkills at commit 7f2d86d, republished under its MIT licence (© learningmatter-mit). 393 words, ~1,011 tokens.

Download SKILL.mdSave it as .claude/skills/mat-dft-mixing-functionals/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
mat-dft-mixing-functionals
description
Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations.
metadata.category
materials
metadata.venv
cpu

MP2020 Compatibility

Goal

To apply Materials Project 2020 Compatibility schemes to MLIP-predicted energies. This is required for models trained on GGA/GGA+U mixed data (e.g., MPtrj data) when constructing convex hulls or phase diagrams to ensure compatibility with the Materials Project database.

[!IMPORTANT] Do NOT apply this to r2SCAN models. Only use this for models trained on GGA/GGA+U mixed data.

Scientific Context

Why is this needed?

The Materials Project (MP) database mixes calculations from two levels of theory: GGA (PBE) and GGA+U. Transition metals (e.g., Mn, Fe, Co, Ni) are calculated with a Hubbard U correction only when present in oxides or fluorides; otherwise, they use standard PBE. To construct a unified convex hull, MP applies the MP2020 Compatibility scheme (energy shifts) to align these distinct potential energy surfaces.

MLIPs trained on MP data (e.g., MACE-MP-0) typically learn these mixed energies. To accurately predict stability against the MP hull, one must apply the same MP2020 corrections to the MLIP outputs.

Potential Issues

Selective application of U introduces discontinuities in the Potential Energy Surface (PES) that are difficult for MLIPs to model physically.

  • Artifacts: Models may exhibit spurious repulsion or underbinding between U-corrected metals and ligands, as they interpolate between incompatible GGA and GGA+U regimes.
References
  1. MP2020 Framework: Wang, A., Kingsbury, R., McDermott, M. et al. A framework for quantifying uncertainty in DFT energy corrections. Sci Rep 11, 15496 (2021). DOI
  2. Impact on MLIPs: Better without U: Impact of Selective Hubbard U Correction on Foundational MLIPs. arXiv:2601.21056 (2026). link
Show full SKILL.md (144 more words)Show less

Compatible Models

This correction is REQUIRED for:

  • MACE-MH-1 omat_pbe head (default)
  • MACE-MH-0 omat_pbe head
  • MACE-OMAT-0-small, MACE-OMAT-0-medium
  • MACE-MP-small, MACE-MP-medium, MACE-MP-large
  • M3GNet-MP-2021.2.8-PES
  • M3GNet-MP-2021.2.8-DIRECT-PES
  • uma-s-1, uma-s-1p1, uma-m-1p1 (with omat head)

This correction is NOT for:

  • CHGNet (e.g. CHGNet-PES-MatPES-r2SCAN-1M-2026.9)
  • MACE-MATPES-r2SCAN-0
  • TensorNet-MatPES-r2SCAN-v2025.1-PES

[!NOTE] The full list of compatible models can be found in resources/gga-ggau-mixed-mlips.yaml.

Instructions

1. Check Compatibility

Use the check_compatibility.py script to programmatically determine if a model/head requires correction.

bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/check_compatibility.py --name "MACE-MH-1" --head "omat_pbe"
# Exit code 0 if required, 1 if not.
2. Apply Correction to a Structure

Use the apply_correction.py script to calculate the corrected energy for a single structure.

To run on a directory of structure files (batch mode):

bash
# Energy defaults to 0.0 if not specified (useful for just checking corrections)
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/apply_correction.py /path/to/structure_dir/

To run on a specific file with known energy:

bash
${CLAUDE_SKILL_DIR}/../../venv/run cpu python ${CLAUDE_SKILL_DIR}/scripts/apply_correction.py structure.cif --energy -123.45
2. Batch Processing

For referencing or phase diagram generation, apply this correction to every entry before computing E_hull.

Constraints

  • Environment: cpu (requires pymatgen).
  • Input Energy: Must be the total energy in eV (not per atom).

Author: Bowen Deng Contact: GitHub @learningmatter-mit

© learningmatter-mit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/mat-dft-mixing-functionals of learningmatter-mit/AtomisticSkills.

  • SKILL.md
  • resources/gga-ggau-mixed-mlips.yaml
  • scripts/apply_correction.py
  • scripts/check_compatibility.py

Open the folder on GitHubat commit 7f2d86d

Compare with similar skills

Mat Dft Mixing Functionals 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 Mixing Functionals compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mat Dft Mixing Functionals this skilllearningmatter-mit/AtomisticSkills175—~1kAutomated safety check: PassMIT
Correctcursor/plugins10k3 repos~612Automated safety check: PassNone
CorrectionNxcoreAI/EverRoom3k—~290Automated safety check: PassCustom licence
Azure Functionsdavila7/claude-code-templates32k1 repos~344Automated safety check: PassMIT
Energy Procurementaffaan-m/ECC274k4 repos~7.4kAutomated safety check: PassApache-2.0
Energy Procurementaffaan-m/ECC274k2 repos~2.5kAutomated safety check: PassApache-2.0

Similar skills

  • Correct

    cursor/plugins

    Official

    Find the mistakes agents keep repeating in this repo and make each one impossible.

    10k GitHub starsUsed in 3 repos~612 tokens
    Auto-check passed

  • Correction

    NxcoreAI/EverRoom

    Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.

    3k GitHub stars~290 tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Azure Functions

    davila7/claude-code-templates

    Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns.

    32k GitHub starsUsed in 1 repo~344 tokens
    Backend & APIsAuto-check passed

  • Energy Procurement

    affaan-m/ECC

    Procure electricity and natural gas for commercial and industrial facilities: tariff and rate-schedule optimization, demand-charge mitigation, supplier RFPs, fixed/index/block-and-index hedging…

    274k GitHub starsUsed in 4 repos~7.4k tokens
    Business, Finance & HRAuto-check passed

  • Energy Procurement

    affaan-m/ECC

    电力与燃气采购、电价优化、需量电费管理、可再生能源购电协议评估及多设施能源成本管理的编码化专业知识。基于能源采购经理在大型工商业用户中超过15年的经验。包括市场结构分析、对冲策略、负荷分析和可持续性报告框架。适用于采购能源、优化电价、管理需量电费、评估购电协议或制定能源策略时使用。

    274k GitHub starsUsed in 2 repos~2.5k tokens
    Business, Finance & HRAuto-check passed

  • Energy Procurement

    sickn33/agentic-awesome-skills

    Codified expertise for electricity and gas procurement, tariff optimisation, demand charge management, renewable PPA evaluation, and multi-facility energy cost management.

    47k GitHub starsUsed in 2 repos~7.4k tokens
    Business, Finance & HRAuto-check passed

More from learningmatter-mit/AtomisticSkills

All 129 skills in this repo

  • Drug Binding Site Definition

    learningmatter-mit/AtomisticSkills

    Define a docking search box (center coordinates + box dimensions in Angstroms) from a co-crystal ligand, binding-site residues, or a saved JSON specification.

    175 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Drug Complex System Builder

    learningmatter-mit/AtomisticSkills

    Build a solvated, charge-neutralized protein-ligand complex for OpenMM molecular dynamics simulation.

    175 GitHub stars~2k tokensUpdated yesterday
    Auto-check passed

  • Drug Pocket Detection

    learningmatter-mit/AtomisticSkills

    Identify and rank ligandable pockets on a protein structure or model using geometry (fpocket) or an ML predictor (P2Rank).

    175 GitHub stars~4k tokensUpdated yesterday
    Auto-check passed

  • Chem Bond Dissociation

    learningmatter-mit/AtomisticSkills

    Calculate homolytic and heterolytic bond dissociation energies (BDEs) for all single bonds in a molecule using MLIPs with RDKit fragmentation.

    175 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Chem Conformer Search

    learningmatter-mit/AtomisticSkills

    Generate molecular conformers with RDKit ETKDG, relax with MLIPs, and rank by energy with Boltzmann weighting.

    175 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

  • Chem DB Mof

    learningmatter-mit/AtomisticSkills

    Query multiple MOF databases (QMOF via MPContribs; ARC-MOF DB7/Majumdar et al.

    175 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Questions about Mat Dft Mixing Functionals

What does Mat Dft Mixing Functionals do?

Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations. Mat Dft Mixing Functionals is an agent skill from learningmatter-mit/AtomisticSkills. Energy corrections needed when using certain MLIPs for phase diagram construction / formation energy calculations.

How do I install Mat Dft Mixing Functionals in Claude Code?

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

How do I install Mat Dft Mixing Functionals in Codex?

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

Can I use Mat Dft Mixing Functionals 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-mixing-functionals -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-mixing-functionals, .gemini/skills/mat-dft-mixing-functionals, .github/skills/mat-dft-mixing-functionals and .opencode/skills/mat-dft-mixing-functionals in your project.

What does Mat Dft Mixing Functionals need to run?

Going by SKILL.md and its folder, Mat Dft Mixing Functionals needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Mat Dft Mixing Functionals access the network?

SKILL.md names 4 domains. As links in the text: pymatgen.org, doi.org, arxiv.org and github.com. This is read from the text; nothing was executed.

Is Mat Dft Mixing Functionals 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 Mixing Functionals use?

Mat Dft Mixing Functionals 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 Mixing Functionals use?

About 1k tokens (SKILL.md is roughly 4k 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 Mixing Functionals?

Skills that share tags, products or a category with Mat Dft Mixing Functionals: Correct (cursor/plugins, 10k stars), Correction (NxcoreAI/EverRoom, 3k stars), Azure Functions (davila7/claude-code-templates, 32k stars) and Energy Procurement (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Mat Dft Mixing Functionals?

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.

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.