Uma
lamm-mit/scienceclaw
Run structure relaxation and phonon calculations using Meta's UMA (Universal Materials Accelerator) via fairchem
Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
Install ML Generative Adit
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-adit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ml-generative-adit .claude/skills/ml-generative-adit && rm -rf skills-srcUse ~/.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/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .claude/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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 install https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-aditType 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.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-adit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ml-generative-adit .agents/skills/ml-generative-adit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .agents/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-adit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ml-generative-adit .cursor/skills/ml-generative-adit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .cursor/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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 https://github.com/learningmatter-mit/AtomisticSkills.git --path skills/ml-generative-adit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-adit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ml-generative-adit .gemini/skills/ml-generative-adit && rm -rf skills-srcUse ~/.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/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .gemini/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-aditInstalls 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).
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ml-generative-adit .github/skills/ml-generative-adit && rm -rf skills-srcUse ~/.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/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .github/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-adit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ml-generative-adit .opencode/skills/ml-generative-adit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ml-generative-adit" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-adit into .opencode/skills/ml-generative-adit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-adit", 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
ml-generative-adit- GitHub stars
- 175
- Token cost
- ~1.4k tokens
- SKILL.md length
- 543 words
- Files
- 13
- Skills in repo
- 129
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
- Works in 9 steps: Prerequisites → Available Models → MCP Tool Usage → …
- Tasks that involve Physical and earth sciences
- SKILL.md covers Goal, 1. Prerequisites, 2. Available Models and 3. MCP Tool Usage, plus 6 more sections
- Calls git; reaches github.com
What it does
ML Generative Adit is an agent skill from learningmatter-mit/AtomisticSkills. Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files (for example `examples/molecules/README.md` and `examples/molecules/generation_metadata.json`).
It sits in AI & LLM Engineering, covering Physical and earth sciences, Creative writing and fiction and Diffusion and image models. It works with CUDA. 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 Physical and earth sciences
- Tasks that involve Creative writing and fiction
- Tasks that involve Diffusion and image models
Example prompts
- “/ml-generative-adit”
Workflow steps
9 steps, taken from the step headings in SKILL.md.
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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
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 Generative Adit loads about 1.4k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 543 words of instructions outside code blocks.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from learningmatter-mit/AtomisticSkills at commit 7f2d86d, republished under its MIT licence (© learningmatter-mit). 543 words, ~1,373 tokens.
Download SKILL.mdSave it as
.claude/skills/ml-generative-adit/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.- name
- ml-generative-adit
- description
- Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
- metadata.category
- machine-learning, materials, chemistry
ADiT Structure Generation Skill
Goal
Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformers, ICML 2025), a unified latent diffusion framework from Meta FAIR Chemistry that jointly generates both periodic materials and non-periodic molecular systems from a shared latent space.
1. Prerequisites
[!IMPORTANT] GPU Required: ADiT requires a CUDA-compatible GPU. CPU inference is extremely slow.
Runs as the
aditMCP server and its scripts run in theaditenvironment: on x86_64 a uv environment created on first use (CUDA 12.6 or 13 by driver), on aarch64 thegenerativecontainer image.The AADT repository cloned next to this project as
../adit, or anywhere withADIT_REPOpointing to it, at the verified commit.venv/runmounts it into the container on aarch64.bash git clone https://github.com/facebookresearch/all-atom-diffusion-transformer ${CLAUDE_SKILL_DIR}/../../../adit git -C ${CLAUDE_SKILL_DIR}/../../../adit checkout b9ce505f170597a7c8ca50d13ce8e15df21cf8c9Pre-trained weights are automatically downloaded from HuggingFace on first use.
2. Available Models
ADiT provides a joint pre-trained model trained on:
- MP20: Materials Project 2020 dataset (inorganic crystals, ~45K structures)
- QM9: Small organic molecules (~134K molecules)
The single checkpoint handles both crystal and molecule generation, selected via the generation_type parameter.
3. MCP Tool Usage
Crystal Generation
Generate novel periodic crystal structures (saved as CIF files):
adit.generate_structures(
generation_type="crystals", # Generate periodic crystals
num_structures=10, # Number of structures to generate
batch_size=100, # Batch size for GPU efficiency
cfg_scale=2.0, # Classifier-free guidance scale
output_dir="research/my_project/crystals"
)Molecule Generation
Generate novel non-periodic molecules (saved as XYZ files):
adit.generate_structures(
generation_type="molecules", # Generate molecules
num_structures=10,
batch_size=100,
cfg_scale=2.0,
output_dir="research/my_project/molecules"
)4. Parameters
| Parameter | Default | Description |
|---|---|---|
generation_type | "crystals" | "crystals" for periodic structures (CIF), "molecules" for non-periodic (XYZ) |
num_structures | 10 | Total number of structures to generate |
batch_size | 100 | Batch size (larger = faster on GPU) |
cfg_scale | 2.0 | Classifier-free guidance scale. Higher = more typical but less diverse |
device | "auto" | Device: "auto", "cpu", or "cuda" |
output_dir | auto | Output directory. Auto-creates under research dir |
5. Output Files
Crystal Generation
crystal_XXXX.cif: Generated crystal structure files (pymatgen CIF format)generation_metadata.json: Generation parameters and statistics
Molecule Generation
molecule_XXXX.xyz: Generated molecule files (ASE XYZ format)generation_metadata.json: Generation parameters and statistics
Show full SKILL.md (257 more words)Show less
6. Limitations
[!WARNING] No Conditional Generation: The public checkpoint is unconditional only — you cannot condition on specific compositions, space groups, or properties. To get specific compositions: generate many structures and filter.
[!WARNING] No Fine-Tuning via MCP: Fine-tuning requires the full AADT training pipeline with multi-GPU setup and wandb logging. Use the raw codebase for training.
[!NOTE] Atom Count Distribution: The number of atoms per generated structure is sampled from the training dataset distribution. For crystals (MP20), this peaks around 8-20 atoms. For molecules (QM9), this peaks around 18 atoms including hydrogens.
7. Best Practices
[!TIP]
- Start with crystals: Crystal generation on MP20 tends to produce more valid structures
- Guidance scale: Use 2.0 (default) for balanced diversity/quality. Increase to 3.0-4.0 for more "typical" structures
- Validate outputs: Always validate generated structures via relaxation and stability analysis
- Batch size: Use batch_size=100 for best GPU throughput
8. Workflow Integration
ADiT works well in combination with:
- Structure relaxation: Use MLIP tools (MACE, FairChem, MatGL) to optimize generated structures
- Stability analysis: Calculate E_hull to identify thermodynamically stable phases
- Property prediction: Use MLIPs or DFT to calculate properties of generated structures
- Comparison with MatterGen: Generate structures with both ADiT and MatterGen for diversity
9. Architecture
ADiT uses a two-stage latent diffusion approach:
- VAE Autoencoder: Maps all-atom representations (atoms, coords, lattice) to a shared latent space
- DiT Denoiser: Trained via flow matching to generate new latent embeddings
- Decoder: Converts latent embeddings back to atomic structures
This unified framework handles both periodic (crystals) and non-periodic (molecules) systems.
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 12 other files in skills/ml-generative-adit of learningmatter-mit/AtomisticSkills.
- SKILL.md
- examples/molecules/README.md
- examples/molecules/generation_metadata.json
- examples/molecules/molecule_0000.xyz
- examples/molecules/molecule_0001.xyz
- examples/molecules/molecule_0002.xyz
- examples/molecules/molecule_0003.xyz
- examples/molecules/molecule_0004.xyz
- examples/molecules/molecule_0005.xyz
- examples/molecules/molecule_0006.xyz
- examples/molecules/molecule_0007.xyz
- examples/molecules/molecule_0008.xyz
- examples/molecules/molecule_0009.xyz
Open the folder on GitHubat commit 7f2d86d
Compare with similar skills
ML Generative Adit 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| ML Generative Adit this skilllearningmatter-mit/AtomisticSkills | 175 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Umalamm-mit/scienceclaw | 244 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Character Refseternityspring/shuohao-skills | 4.2k | — | ~1.7k | Automated safety check: Warn | Apache-2.0 | |
| AI Research Explorelllllllama/RigorPilot-Skills | 497 | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Triton Sageattentionartokun/comfyui-mcp | 793 | — | ~5k | Automated safety check: Pass | MIT | |
| Comfy CLIsundial-org/awesome-openclaw-skills | 663 | — | ~1.5k | Automated safety check: Pass | None |
Similar skills
Character Refs
eternityspring/shuohao-skills
给任何故事里的角色真出参考图（小说改编、自己原创的故事、单独设计一个角色都行，不需要小说原文）： 一段话描述角色，拆成分层字段、补全后确认， 先出一张正面全身锚点，其余视图（大头照、90° 侧面、背面、细节、45° 大头照）都只参考这张锚点， 按需分档出图。每张图带标识、可单独重出，重出后自动标出哪些图过期。
AI Research Explore
lllllllama/RigorPilot-Skills
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates.
Triton Sageattention
artokun/comfyui-mcp
Install Triton + SageAttention to accelerate ComfyUI (the sageattn attentionmode and inductor torch.compile used by WanVideoWrapper / many video graphs).
Comfy CLI
sundial-org/awesome-openclaw-skills
Install, manage, and run ComfyUI instances. An agent skill from sundial-org/awesome-openclaw-skills.
Esmfold2
JimLiu/science-skills
Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.
More from learningmatter-mit/AtomisticSkills
All 129 skills in this repoDrug 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.
Drug Complex System Builder
learningmatter-mit/AtomisticSkills
Build a solvated, charge-neutralized protein-ligand complex for OpenMM molecular dynamics simulation.
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).
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.
Chem Conformer Search
learningmatter-mit/AtomisticSkills
Generate molecular conformers with RDKit ETKDG, relax with MLIPs, and rank by energy with Boltzmann weighting.
Chem DB Mof
learningmatter-mit/AtomisticSkills
Query multiple MOF databases (QMOF via MPContribs; ARC-MOF DB7/Majumdar et al.
Related
Works with
Questions about ML Generative Adit
What does ML Generative Adit do?
Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model. ML Generative Adit is an agent skill from learningmatter-mit/AtomisticSkills. Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.
When should I use ML Generative Adit?
ML Generative Adit fits situations like: tasks that involve Physical and earth sciences; tasks that involve Creative writing and fiction; tasks that involve Diffusion and image models.
How do I install ML Generative Adit in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a claude-code`. Or copy the skill folder (skills/ml-generative-adit in learningmatter-mit/AtomisticSkills) into .claude/skills/ml-generative-adit in your project. Claude Code loads it when a task matches its description.
How do I install ML Generative Adit in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-adit -a codex`. Or copy the skill folder (skills/ml-generative-adit in learningmatter-mit/AtomisticSkills) into .agents/skills/ml-generative-adit in your project. Codex loads it when a task matches its description.
Can I use ML Generative Adit 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-generative-adit -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-generative-adit, .gemini/skills/ml-generative-adit, .github/skills/ml-generative-adit and .opencode/skills/ml-generative-adit in your project.
What does ML Generative Adit need to run?
Going by SKILL.md and its folder, ML Generative Adit needs the command-line tools its instructions call (git).
Does ML Generative Adit access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is ML Generative Adit 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. Review the folder before installing.
What licence does ML Generative Adit use?
ML Generative Adit 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 Generative Adit use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 ML Generative Adit?
Skills that share tags, products or a category with ML Generative Adit: Uma (lamm-mit/scienceclaw, 244 stars), Character Refs (eternityspring/shuohao-skills, 4.2k stars), AI Research Explore (lllllllama/RigorPilot-Skills, 497 stars) and Triton Sageattention (artokun/comfyui-mcp, 793 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ML Generative Adit?
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.