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

ML Mlip Speed

by learningmatter-mit in learningmatter-mit/AtomisticSkills

Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).

MITAuto-check passedData & Analytics

Install ML Mlip Speed

skills CLI
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-mlip-speed -a claude-code

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

GitHub CLI
$ gh skill install learningmatter-mit/AtomisticSkills ml-mlip-speed --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/ml-mlip-speed .claude/skills/ml-mlip-speed && 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
ml-mlip-speed
GitHub stars
175
Token cost
~1k tokens
SKILL.md length
436 words
Files
5 (incl. scripts)
Skills in repo
129
Repo updated
First seen
Licence
MIT

At a glance

Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).

  • Works in 2 steps: Run the script in each environment: The… → Consolidate: Run the script in any…
  • Tasks that involve Machine learning
  • SKILL.md covers Goal, Benchmark Script, Typical Performance (NVIDIA… and Resources
  • Runs Python scripts from its folder

What it does

ML Mlip Speed is an agent skill from learningmatter-mit/AtomisticSkills. Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `resources/speed_benchmark_dgx_spark.yaml` and `scripts/benchmark_mlips.py`).

It sits in Data & Analytics, covering Machine learning. The repository describes itself as: Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc). The licence is MIT.

When your agent uses it

  • Tasks that involve Machine learning

Example prompts

  • “/ml-mlip-speed”

Requirements

  • Python 3

Workflow steps

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

  1. Run the script in each environment: The script gracefully skips models whose libraries are missing while preserving and updating the…
  2. Consolidate: Run the script in any environment (that has matplotlib) with the --only_plot flag to generate the combined graphs from the…

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 1 file 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

ML Mlip Speed loads about 1k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 436 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
~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). 436 words, ~1,040 tokens.

Download SKILL.mdSave it as .claude/skills/ml-mlip-speed/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
ml-mlip-speed
description
Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).
metadata.category
machine-learning
metadata.venv
fairchem, mlip

MLIP Performance Benchmarking

Goal

Evaluate and compare the inference speed (latency) and memory consumption of various foundation MLIP models to determine their suitability for different simulation scales and timescales.

Benchmark Script

The benchmark_mlips.py script measures performance by running short MD simulations on NaCl supercells of varying sizes.

Usage

Run the script once per environment: mlip covers MACE and MatGL, fairchem covers FairChem. The script automatically skips models not supported by the current environment.

Multi-Environment Benchmarking

Because FairChem cannot share an environment with MACE (their e3nn requirements conflict), the benchmark results are built incrementally.

  1. Run the script in each environment: The script gracefully skips models whose libraries are missing while preserving and updating the central speed_benchmark.yaml file.
  2. Consolidate: Run the script in any environment (that has matplotlib) with the --only_plot flag to generate the combined graphs from the accumulated total data.
bash
# One run per environment; each adds to the shared results file
${CLAUDE_SKILL_DIR}/../../venv/run mlip python ${CLAUDE_SKILL_DIR}/scripts/benchmark_mlips.py --output_dir results/
${CLAUDE_SKILL_DIR}/../../venv/run fairchem python ${CLAUDE_SKILL_DIR}/scripts/benchmark_mlips.py --output_dir results/

# Generate final combined plots
${CLAUDE_SKILL_DIR}/../../venv/run mlip python ${CLAUDE_SKILL_DIR}/scripts/benchmark_mlips.py --only_plot --output_dir results/

Key Arguments:

  • --models: List of model names/checkpoints to benchmark.
  • --providers: Corresponding providers (mace, matgl, fairchem).
  • --output_dir: Directory to save results and plots.
  • --max_atoms_limit: Maximum system size to test (default: 5000).
  • --only_plot: Re-generate plots from an existing speed_benchmark.yaml file without running simulations.
Metrics Explained
  • Inference Time / Atom (ms): The normalized time taken for a single force/energy calculation per atom. Converged values (for larger systems) provide the best comparison.
  • Memory Usage / Atom (MB): The peak VRAM footprint per atom. Useful for predicting OOM (Out Of Memory) limits for large supercells.
Show full SKILL.md (206 more words)Show less

Typical Performance (NVIDIA GB10)

Performance benchmarks conducted on NVIDIA GB10 reveal distinct performance tiers:

  • High Speed / Low Cost: Models like M3GNet and TensorNet scale efficiently to large systems (>10,000 atoms) with very low latency (~0.1 ms/atom).
  • Intermediate: MACE small/medium models and eSEN models occupy the mid-range (~0.3 - 1.0 ms/atom).
  • High Accuracy / High Cost: MACE-MH-1 and UMA-medium are heavier (~1.5 - 4.0 ms/atom), making them ideal for static calculations or small-scale MD.
Optimal System Size and Overhead

[!IMPORTANT] Constant Overhead: MLIP inference on GPUs has a significant constant overhead (fixed cost regardless of system size). For very small systems (<100 atoms), the inference time per atom is dominated by this overhead, resulting in poor efficiency.

Best Practice: For capturing chemical rare events or maximizing throughput, it is more efficient to use larger cells of ~500 atoms. At this size, the constant overhead is amortized, allowing the MLIP to operate closer to its peak theoretical throughput while providing a larger volume for sampling transitions.

Image: Inference Speed Image: Memory Usage

[!TIP] Use these results to select models for long MD simulations or large-scale screening. For systems >1000 atoms, prioritize models with latency < 0.5 ms/atom if ns-scale MD is required.

Resources

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 4 other files (scripts) in skills/ml-mlip-speed of learningmatter-mit/AtomisticSkills.

  • SKILL.md
  • examples/inference_speed_nvidia_gb10.png
  • examples/memory_usage_nvidia_gb10.png
  • resources/speed_benchmark_dgx_spark.yaml
  • scripts/benchmark_mlips.py

Open the folder on GitHubat commit 7f2d86d

Compare with similar skills

ML Mlip Speed 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.

ML Mlip Speed compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
ML Mlip Speed this skilllearningmatter-mit/AtomisticSkills175—~1kAutomated safety check: PassMIT
Scikit LearnzLanqing/codex-claude-academic-skills4.6k17 repos~3.9kAutomated safety check: PassBSD-3-Clause
Senior Data ScientistRaidriar7170/hermes-skilleval1256 repos~1.4kAutomated safety check: PassMIT
Agentic Kaggle WorkflowFrankS-IntelLab/agentic-kaggle-skill188—~4kAutomated safety check: PassMIT
Retention Analysisliangdabiao/claude-data-analysis-ultra-main2901 repos~1.3kAutomated safety check: NotesNone
Geomlitalo-goncalves/geoML108—~4.2kAutomated safety check: PassGPL-3.0

Similar skills

  • Scikit Learn

    zLanqing/codex-claude-academic-skills

    Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.

    4.6k GitHub starsUsed in 17 repos~3.9k tokens
    Data & AnalyticsAuto-check passed

  • Senior Data Scientist

    Raidriar7170/hermes-skilleval

    World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.

    125 GitHub starsUsed in 6 repos~1.4k tokens
    Data & AnalyticsAuto-check passed

  • Agentic Kaggle Workflow

    FrankS-IntelLab/agentic-kaggle-skill

    Takes a Kaggle competition from rules and validation design through baselines, ensembling and notebook architecture to a scored submission.

    188 GitHub stars~4k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

  • Retention Analysis

    liangdabiao/claude-data-analysis-ultra-main

    Analyze user retention and churn using survival analysis, cohort analysis, and machine learning.

    290 GitHub starsUsed in 1 repo~1.3k tokens
    Data & AnalyticsAuto-check: notes

  • Geoml

    italo-goncalves/geoML

    Working knowledge of the geoML Python package (github.com/italo-goncalves/geoML): variational Gaussian processes for spatial data, implicit geological modelling, block models, drillhole data…

    108 GitHub stars~4.2k tokensUpdated 5 days ago
    Data & AnalyticsAuto-check passed

  • Radiomics ML

    Aperivue/medsci-skills

    A skill your agent uses when building or auditing a radiomics or tabular clinical-ML prediction model with a classical learner (LASSO, SVM, random forest, XGBoost and similar).

    329 GitHub starsUsed in 1 repo~2.7k tokens
    Data & AnalyticsAuto-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

Categories

Questions about ML Mlip Speed

What does ML Mlip Speed do?

Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs). ML Mlip Speed is an agent skill from learningmatter-mit/AtomisticSkills. Benchmark of inference speed of Machine Learning Interatomic Potentials (MLIPs).

When should I use ML Mlip Speed?

ML Mlip Speed fits situations like: tasks that involve Machine learning.

How do I install ML Mlip Speed in Claude Code?

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

How do I install ML Mlip Speed in Codex?

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

Can I use ML Mlip Speed 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 ml-mlip-speed -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ml-mlip-speed, .gemini/skills/ml-mlip-speed, .github/skills/ml-mlip-speed and .opencode/skills/ml-mlip-speed in your project.

What does ML Mlip Speed need to run?

Going by SKILL.md and its folder, ML Mlip Speed needs Python for the scripts in its folder. Our summary lists: Python 3.

Does ML Mlip Speed 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 ML Mlip Speed 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 ML Mlip Speed use?

ML Mlip Speed 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 ML Mlip Speed use?

About 1k tokens (SKILL.md is roughly 4.2k 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 ML Mlip Speed?

Skills that share tags, products or a category with ML Mlip Speed: Scikit Learn (zLanqing/codex-claude-academic-skills, 4.6k stars), Senior Data Scientist (Raidriar7170/hermes-skilleval, 125 stars), Agentic Kaggle Workflow (FrankS-IntelLab/agentic-kaggle-skill, 188 stars) and Retention Analysis (liangdabiao/claude-data-analysis-ultra-main, 290 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains ML Mlip Speed?

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.