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/chem-nmr-predictnpx skills add learningmatter-mit/AtomisticSkills --skill chem-nmr-predictgit 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/chem-nmr-predict)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-nmr-predict"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-nmr-predict.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 | $0.00037 | $0.01744 |
| Opus 5 | $0.00018 | $0.00872 |
| Sonnet 5 | $0.00007 | $0.00349 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
chem-nmr-predict 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 5d ago.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1H NMR Spectrum Prediction
When to Use This Skill
The agent should use this skill when:
- A SMILES string is known and the agent needs a predicted 1H NMR spectrum (ppm vs intensity) for that compound.
- The agent needs a signal list (chemical shifts, multiplicities, coupling constants, proton counts) for a compound.
- Reference spectra are needed for mixture deconvolution (called by the
chem-nmr-analysisskill). - The user wants to compare a predicted spectrum against an experimental one for structure confirmation.
When NOT to Use This Skill
- The user already has an experimental or digitized spectrum file — no prediction is needed; the agent should use the existing file directly.
- The user has a compound name but not a SMILES — the agent should first resolve the name to SMILES using the
drug-db-pubchemskill, then call this skill. - 13C NMR prediction — this skill predicts 1H NMR only. The NMRdb.org SPINUS endpoint does not support 13C.
- Polymers, organometallics, or molecules with >50 heavy atoms — the SPINUS neural network may not produce reliable predictions, and nmrsim QM simulation is limited to ~11 coupled spins per spin system.
- The user asks about reaction products or mixture composition — the agent should use
chem-nmr-analysisinstead, which calls this skill internally.
Workflow: SMILES → Predicted 1H NMR
Step 1 — Ensure SMILES Are Available
If the user provides compound names instead of SMILES, the agent should first resolve them:
# Env: base-agent
python .agents/skills/drug-db-pubchem/scripts/query_pubchem.py \
--name "camphor" --outdir <research_dir>/pubchem/
The agent should extract CanonicalSMILES from the JSON output.
If PubChem returns no results, the agent should try alternate names or ask the user to provide the SMILES directly.
Step 2 — Predict NMR Spectra
# Env: nmr-agent
python .agents/skills/chem-nmr-predict/scripts/predict_nmr.py \
--smiles "<smiles_1>" "<smiles_2>" \
--names "compound1" "compound2" \
--field_mhz 400 \
--output_dir <research_dir>/nmr_predictions/
What ships with it
1 file 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.
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.
- 5d ago First seen · 134 lines · 37 tokens per session scan A 3224f36a15b2
chem-nmr-predict is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (160 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,744 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 2026-08-30.
Other skills, from other repositories
datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters…
deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first…
hypogenic
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use…
rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…
molfeat
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
pytdc
Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.