Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/learningmatter-mit/atomisticskills/ml-generative-diffcspnpx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-diffcspgit clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/learningmatter-mit/atomisticskills/ml-generative-diffcsp)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/ml-generative-diffcsp"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/ml-generative-diffcsp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00036 | $0.01321 |
| Opus 5 | $0.00018 | $0.00660 |
| Sonnet 5 | $0.00007 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
ml-generative-diffcsp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DiffCSP++ Crystal Structure Generation
Goal
Generate novel crystal structures using DiffCSP++ (ICLR 2024), a diffusion model that leverages space group symmetry constraints for crystal structure prediction (CSP) and ab initio generation.
1. Prerequisites
[!IMPORTANT] GPU Required: DiffCSP++ inference is significantly faster on GPU.
- The
diffcsp-agentconda environment must be installed. - DiffCSP++ repo cloned to
/home/bdeng/projects/DiffCSP-PP. - Pre-trained checkpoints downloaded to
checkpoints/directory.
2. Available Models
| Model | Type | Description |
|---|---|---|
mp_csp |
CSP | Materials Project — composition-constrained generation |
mp_gen |
Gen | Materials Project — unconditional generation |
perov_csp |
CSP | Perovskite — composition-constrained generation |
perov_gen |
Gen | Perovskite — unconditional generation |
carbon_gen |
Gen | Carbon — unconditional generation |
mpts_csp |
CSP | MPTS-52 — composition-constrained generation |
3. Usage Modes
Mode 1: Single Composition via MCP Tool (Recommended)
Generate structures with exact composition using the generate_structures_with_symmetry MCP tool:
mcp_diffcsp_generate_structures_with_symmetry(
spacegroup=58, # Space group number (1-230)
wyckoff_letters="2a,2d,4g", # Wyckoff positions (comma-separated or shorthand "adg")
atom_types="Mn,Li,O", # Element per Wyckoff position
model_name="mp_csp", # CSP model
num_samples=5, # Number of structures to generate
step_lr=1e-5, # Langevin step size
output_dir="research/my_project"
)
Mode 2: Batch Generation from JSON File
Generate multiple structures from a JSON specification file. This is useful when you have many different compositions to generate at once.
JSON format (see examples/example.json):
[
{"spacegroup_number": 58, "wyckoff_letters": ["2a","2d","4g"], "atom_types": ["Mn","Li","O"]},
{"spacegroup_number": 194, "wyckoff_letters": "abff", "atom_types": ["Tm","Tm","Ni","As"]}
]
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/batch-json/generation_metadata.json 128 B
- examples/batch-json/README.md 908 B
- examples/batch-json/structure_0000.cif 1.0 KB
- examples/batch-json/structure_0001.cif 1.3 KB
- examples/example.json 415 B
- examples/Li2ZrCl6-symmetry/generation_metadata.json 315 B
- examples/Li2ZrCl6-symmetry/README.md 820 B
- examples/Li2ZrCl6-symmetry/structure_0000.cif 1.6 KB
- examples/Li2ZrCl6-symmetry/structure_0001.cif 1.6 KB
- examples/Li2ZrCl6-symmetry/structure_0002.cif 1.6 KB
- examples/unconditional/generation_metadata.json 142 B
- examples/unconditional/README.md 899 B
- examples/unconditional/structure_0000.cif 1.2 KB
- examples/unconditional/structure_0001.cif 2.7 KB
- examples/unconditional/structure_0002.cif 1.3 KB
- examples/unconditional/structure_0003.cif 2.0 KB
- examples/unconditional/structure_0004.cif 2.7 KB
- scripts/batch_generate.py 3.3 KB runs code
- scripts/unconditional_generate.py 2.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 126 lines · 36 tokens per session scan A 3a83279b8908
ml-generative-diffcsp is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (158 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 1,321 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
hugging-face-trackio
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API) or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, HF Space syncing, and JSON output for automation.
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
HomeSafe-Bench
VLM indoor safety hazard detection benchmark inspired by HomeSafeBench (arXiv 2509.23690).
implement-tool
Implements a new bioinformatics tool wrapper in proto-tools using a parallelized agent pipeline. Orchestrates phases: Research, Contract (core tool file), Fan-out (5 parallel subagents), Verify, then the decisive gates — Config Field Audit, Temp Integration & Stress, Docs Verification, Self-Audit & Full PR Review …