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 skills add learningmatter-mit/AtomisticSkills --skill chem-similarity-searchgit 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-similarity-search)<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-similarity-search"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-similarity-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/learningmatter-mit/atomisticskills/chem-similarity-search"><img src="https://agentmods.dev/badge/skills/learningmatter-mit/atomisticskills/chem-similarity-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00030 | $0.00627 |
| Opus 5 | $0.00015 | $0.00313 |
| Sonnet 5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
chem-similarity-search 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 9d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chemical Similarity Search
Goal
To programmatically find chemical analogs, alternative precursors, and structurally similar compounds for a given target molecule using PubChem's "fastsimilarity_2d" endpoint. The skill retrieves lists of similar compounds ranked by sequence alignment of their 2D molecular fingerprints, providing CIDs, molecular weights, formulas, and SMILES strings.
Instructions
1. Search by SMILES String
Search for similar compounds by providing the canonical or isomeric SMILES.
Adjust the --threshold (similarity cutoff 0-100, default is 95) to widen or narrow the search radius. Higher threshold equals higher similarity.
Adjust --max_records to limit the output length.
# Env: base-agent
python .agents/skills/chem-similarity-search/scripts/similarity_search.py \
--smiles "CC(=O)Oc1ccccc1C(=O)O" \
--threshold 95 \
--max_records 5 \
--outdir research/aspirin_similar \
--output aspirin_similar.json
2. Search by PubChem CID
Search directly using an exact compound's CID. This avoids translation steps for SMILES parsing.
# Env: base-agent
python .agents/skills/chem-similarity-search/scripts/similarity_search.py \
--cid 2244 \
--threshold 90 \
--max_records 10 \
--outdir research/aspirin_similar \
--output cid_2244_similar.json
Examples
We can test extracting highly similar analogs (Threshold 95) for Aspirin (CID: 2244 or SMILES: CC(=O)Oc1ccccc1C(=O)O).
# Env: base-agent
python .agents/skills/chem-similarity-search/scripts/similarity_search.py \
--cid 2244 \
--threshold 95 \
--max_records 5 \
--outdir .agents/skills/chem-similarity-search/examples/aspirin_analogs \
--output aspirin_analogs.json
Constraints
- Rate Limiting: PubChem PUG REST API enforces per-user throttling limits. Heavy bursts will result in
HTTP 503 Server Busyerrors. The script implements an exponential backoff retry mechanism. - 2D Similarity: Uses exact structural bit-vector fingerprints. Stereochemical and 3D properties do not strongly affect the score.
- Network: Internet access is required.
What ships with it
3 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.
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.
- 9d ago First seen · 66 lines · 30 tokens per session scan A 5d86e7b3a9d3
chem-similarity-search is a skill published in the GitHub repository learningmatter-mit/AtomisticSkills (162 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 627 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…
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…
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…
binding-affinity
Empirical affinity estimates, ligand energy inspection, docking-score consensus, and batch virtual screening. Full MM/GBSA requires a validated external workflow.
drug-design
End-to-end drug discovery pipeline orchestration. Deterministic Python script that auto-chains structure prediction, pocket detection, de novo design, docking, scoring, and ADMET filtering into reproducible workflows.
molecular-optimization
Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. Paper-backed (MT-Mol, DrugR, MultiMol).