Torchdrug
davila7/claude-code-templates
Graph-based drug discovery toolkit. An agent skill from davila7/claude-code-templates.
Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network.
Install Chem Msms Predict
$ npx skills add learningmatter-mit/AtomisticSkills --skill chem-msms-predict -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills chem-msms-predict --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/chem-msms-predict .claude/skills/chem-msms-predict && 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 "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .claude/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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/chem-msms-predictType 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 chem-msms-predict -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills chem-msms-predict --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/chem-msms-predict .agents/skills/chem-msms-predict && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .agents/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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 chem-msms-predict -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills chem-msms-predict --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/chem-msms-predict .cursor/skills/chem-msms-predict && 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 "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .cursor/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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/chem-msms-predict--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 chem-msms-predict -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills chem-msms-predict --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/chem-msms-predict .gemini/skills/chem-msms-predict && 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 "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .gemini/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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 chem-msms-predictInstalls 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 chem-msms-predict -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/chem-msms-predict .github/skills/chem-msms-predict && 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 "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .github/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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 chem-msms-predict -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 chem-msms-predict --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/chem-msms-predict .opencode/skills/chem-msms-predict && 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 "chem-msms-predict" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/chem-msms-predict into .opencode/skills/chem-msms-predict/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chem-msms-predict", 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
chem-msms-predict- GitHub stars
- 176
- Token cost
- ~1.6k tokens
- SKILL.md length
- 609 words
- Files
- 5 (incl. scripts)
- Skills in repo
- 129
- Repo updated
- First seen
- Licence
- MIT
At a glance
Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network.
- Works in 3 steps: Run inference and generate spectrum → Inspect fragment assignments (optional) → Compare with experimental spectrum…
- Tasks that involve Drug discovery and cheminformatics
- SKILL.md covers Goal, When to Use This Skill, When NOT to Use This Skill and Prerequisites, plus 4 more sections
- Runs Python scripts from its folder
What it does
Chem Msms Predict is an agent skill from learningmatter-mit/AtomisticSkills. Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network. Outputs predicted m/z vs intensity spectrum, fragment ion SMILES, and a spectrum plot.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `examples/README.md`, `examples/predict_smiles.py` and `scripts/download_weights.py`).
It sits in Research & Science, covering Drug discovery and cheminformatics and Deep 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 Drug discovery and cheminformatics
- Tasks that involve Deep learning
Example prompts
- “/chem-msms-predict”
Requirements
- Python 3
Workflow steps
3 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 6257444. 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):
github.comdoi.org
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
Chem Msms Predict loads about 1.6k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 609 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); the scripts in this folder are not scanned.
SKILL.md
The full file from learningmatter-mit/AtomisticSkills at commit 6257444, republished under its MIT licence (© learningmatter-mit). 609 words, ~1,584 tokens.
Download SKILL.mdSave it as
.claude/skills/chem-msms-predict/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- chem-msms-predict
- description
- Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network. Outputs predicted m/z vs intensity spectrum, fragment ion SMILES, and a spectrum plot.
- metadata.category
- chemistry, drug-discovery
- metadata.venv
- msms
LC-MS/MS Spectrum Prediction
Goal
Predict the LC-MS/MS (tandem mass) spectrum of a molecule given its SMILES string using ICEBERG — a two-stage GNN that first generates a fragmentation DAG (fragment ions) and then predicts their intensities. Output is a predicted spectrum (m/z, intensity) with optional fragment SMILES assignments per peak.
When to Use This Skill
- A SMILES string is known and a predicted LC-MS/MS spectrum (m/z vs intensity) is needed.
- Fragment ion assignments (SMILES per peak) are required.
- No reference spectrum exists, or comparison to a predicted spectrum is desired.
- Companion skill
chem-spectrum-matchercan compare predicted vs experimental spectra.
When NOT to Use This Skill
- Experimental spectrum already available — use it directly; no prediction needed.
- Only compound name known — first resolve to SMILES via
drug-db-pubchem, then call this skill. - GC-MS or other MS types — ICEBERG is trained on LC-MS/MS only; flag a warning before proceeding.
- Organometallics or MW > 1000 — predictions may be unreliable or fail due to unsupported element types.
Prerequisites
Scripts run in the msms environment, created on first use by venv/run. It
installs ICEBERG 2.1 (ms-pred, pinned to a commit) on a CPU torch build, and
is x86_64 Linux only: DGL publishes no aarch64 wheels.
Download the ICEBERG 2.1 checkpoints
${CLAUDE_SKILL_DIR}/../../venv/run msms python ${CLAUDE_SKILL_DIR}/scripts/download_weights.pyThis fetches the public weights trained on MassSpecGym (msg_all, ~80 MB) from
the ms-pred authors:
downloads/iceberg_msg_all/
├── gen/best.ckpt # generator (stage 1)
└── inten_contr/best.ckpt # intensity predictor (stage 2)Weights trained on NIST are available from the ms-pred authors on proof of a NIST license. ICEBERG 2.0 checkpoints do not load: 2.1 adds instrument types. Flag error and stop if either checkpoint is missing.
Instructions
Step 1 — Run inference and generate spectrum
${CLAUDE_SKILL_DIR}/../../venv/run msms python ${CLAUDE_SKILL_DIR}/scripts/predict_msms.py \
--smiles "c1ccccc1C(=O)OCCN" \
--gen_ckpt downloads/iceberg_msg_all/gen/best.ckpt \
--inten_ckpt downloads/iceberg_msg_all/inten_contr/best.ckpt \
--collision_energies 20 40 \
--adduct "[M+H]+" \
--instrument "Orbitrap" \
--output_dir results/msms_predictionKey parameters:
--smiles— input molecule as SMILES string--gen_ckpt/--inten_ckpt— paths to ICEBERG checkpoints--collision_energies— one or more collision energies in eV (e.g.20 40 60); model was trained on absolute eV values--adduct— supported adducts:[M+H]+,[M-H]-,[M+Na]+,[M+NH4]+, and others fromms_pred.common.ion2mass--instrument— instrument type for intensity prediction (e.g."Orbitrap","QTOF")--threshold— confidence cutoff for DAG fragment generator (default0.1; lower = more fragments)--sparse_k— maximum number of peaks returned (default100)--num_workers— parallel CPU workers (default0: serial); inference runs on the CPU
Outputs written to --output_dir:
| File | Description |
|---|---|
spectrum.png | Stem plot of predicted spectrum, one panel per collision energy |
fragments.json | JSON list per CE: {mz, intensity, fragment_smiles} sorted by intensity |
input_configs.yaml | All run parameters for reproducibility |
Show full SKILL.md (231 more words)Show less
Step 2 — Inspect fragment assignments (optional)
fragments.json maps each predicted peak to the fragment ICEBERG assigns it,
as the Kekulé SMILES of the heavy-atom substructure (hydrogen shifts are not
shown). There is one entry per fragment, so fragments with the same formula
repeat an m/z; spectrum.png sums them. For 2-aminoethyl benzoate at 20 eV:
{
"20": [
{"mz": 149.0597, "intensity": 1.0, "fragment_smiles": "CCOC(=O)C1=CC=CC=C1"},
{"mz": 105.0335, "intensity": 0.944, "fragment_smiles": "O=CC1=CC=CC=C1"},
...
]
}Use this to rationalize which bonds fragment at which energy.
Step 3 — Compare with experimental spectrum (optional)
If an experimental spectrum is available, use the companion skill:
Examples
2-Aminoethyl benzoate (c1ccccc1C(=O)OCCN)
${CLAUDE_SKILL_DIR}/../../venv/run msms python ${CLAUDE_SKILL_DIR}/examples/predict_smiles.py \
--gen_ckpt downloads/iceberg_msg_all/gen/best.ckpt \
--inten_ckpt downloads/iceberg_msg_all/inten_contr/best.ckpt \
--output_dir .agents/test/msms_exampleExpected output:
spectrum.png— two-panel spectrum (20 eV + 40 eV)fragments.json— fragment assignments for both energies- Precursor
[M+H]+≈ 166.086 Da
Constraints
- Environment: All scripts run in the
msmsenvironment (venv/run msms, x86_64 Linux only), on the CPU. - Checkpoints required: Script raises
FileNotFoundErrorif--gen_ckptor--inten_ckptare missing. - Collision energy units: Use absolute eV values. To convert NCE → eV, set
nce=Trueiniceberg_prediction()directly. - Non-binned output only: This skill uses
binned_out=False(high-precision m/z). Binned output disables fragment assignment. - Single-compound inference: Provide one SMILES per call. For batch prediction, loop over SMILES and use separate output dirs.
- Unsupported elements: Molecules containing metals, lanthanides, or rare main-group elements may fail or produce low-quality predictions.
- MW limit: ICEBERG is unreliable for MW > 1000 Da.
References
- Alberts, M. et al., "Artificial intelligence for context-aware mass spectrometry", Nature Methods, 2025. DOI:10.1038/s41592-025-02658-z
- ICEBERG source code: github.com/coleygroup/ms-pred
Author: Magdalena Lederbauer Contact: GitHub @mlederbauer
© 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/chem-msms-predict of learningmatter-mit/AtomisticSkills.
- SKILL.md
- examples/README.md
- examples/predict_smiles.py
- scripts/download_weights.py
- scripts/predict_msms.py
Open the folder on GitHubat commit 6257444
Compare with similar skills
Chem Msms Predict 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 |
|---|---|---|---|---|---|---|
| Chem Msms Predict this skilllearningmatter-mit/AtomisticSkills | 176 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Torchdrugdavila7/claude-code-templates | 32k | 12 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Torchdrug Englishaipoch/medical-research-skills | 2k | — | ~2.6k | Automated safety check: Pass | MIT | |
| Rowanlamm-mit/scienceclaw | 244 | 4 repos | ~3.1k | Automated safety check: Warn | Proprietary | |
| Deepchemdavila7/claude-code-templates | 32k | 11 repos | ~4.4k | Automated safety check: Pass | MIT | |
| tangermeme Genomic Model Analysisjmschrei/tangermeme | 311 | — | ~1.6k | Automated safety check: Pass | MIT |
Similar skills
Torchdrug English
aipoch/medical-research-skills
PyTorch-native Graph Neural Network framework for molecules and proteins.
Rowan
lamm-mit/scienceclaw
Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.
Deepchem
davila7/claude-code-templates
Molecular machine learning toolkit. An agent skill from davila7/claude-code-templates.
tangermeme Genomic Model Analysis
jmschrei/tangermeme
Routes agents to the right tangermeme reference for analyzing trained genomic deep learning models, from attributions and motif experiments to variant effects and design.
- Official
Hcls Build Agent
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
A skill your agent uses when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with…
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
Categories
Questions about Chem Msms Predict
What does Chem Msms Predict do?
Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network. Chem Msms Predict is an agent skill from learningmatter-mit/AtomisticSkills. Predict LC-MS/MS (MS2, tandem mass spectra) from SMILES via ICEBERG, a two-stage deep neural network.
When should I use Chem Msms Predict?
Chem Msms Predict fits situations like: tasks that involve Drug discovery and cheminformatics; tasks that involve Deep learning.
How do I install Chem Msms Predict in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill chem-msms-predict -a claude-code`. Or copy the skill folder (skills/chem-msms-predict in learningmatter-mit/AtomisticSkills) into .claude/skills/chem-msms-predict in your project. Claude Code loads it when a task matches its description.
How do I install Chem Msms Predict in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill chem-msms-predict -a codex`. Or copy the skill folder (skills/chem-msms-predict in learningmatter-mit/AtomisticSkills) into .agents/skills/chem-msms-predict in your project. Codex loads it when a task matches its description.
Can I use Chem Msms Predict 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 chem-msms-predict -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chem-msms-predict, .gemini/skills/chem-msms-predict, .github/skills/chem-msms-predict and .opencode/skills/chem-msms-predict in your project.
What does Chem Msms Predict need to run?
Going by SKILL.md and its folder, Chem Msms Predict needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Chem Msms Predict access the network?
SKILL.md names 2 domains. As links in the text: github.com and doi.org. This is read from the text; nothing was executed.
Is Chem Msms Predict 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 Chem Msms Predict use?
Chem Msms Predict 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 Chem Msms Predict use?
About 1.6k tokens (SKILL.md is roughly 6.3k 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 Chem Msms Predict?
Skills that share tags, products or a category with Chem Msms Predict: Torchdrug (davila7/claude-code-templates, 32k stars), Torchdrug English (aipoch/medical-research-skills, 2k stars), Rowan (lamm-mit/scienceclaw, 244 stars) and Deepchem (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Chem Msms Predict?
learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 176 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 7, 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.