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 beita6969/ScienceClaw --skill chemistrygit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/chemistry)<a href="https://agentmods.dev/skills/beita6969/scienceclaw/chemistry"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/chemistry/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/beita6969/scienceclaw/chemistry"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/chemistry.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 | $0.00002 | $0.00434 |
| Opus 5 | $0.00001 | $0.00217 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
chemistry 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 11d 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.
What it actually says
Chemistry & Drug Discovery
Overview
Computational chemistry, cheminformatics, and drug discovery workflows.
Key Tools
- RDKit: Molecular manipulation, fingerprints, descriptors, substructure search
- PubChem: Chemical compound database (100M+ compounds)
- ChEMBL: Bioactivity database for drug-like molecules
- Open Babel: Format conversion, 3D generation
- AutoDock Vina: Molecular docking
- GROMACS/OpenMM: Molecular dynamics simulations
Common Workflows
Virtual Screening
- Define target (protein structure from PDB)
- Prepare compound library (from ChEMBL/ZINC/Enamine)
- Filter by drug-likeness (Lipinski's Rule of Five)
- Docking (AutoDock Vina, GNINA)
- Scoring and ranking
- ADMET prediction (absorption, distribution, metabolism, excretion, toxicity)
- Hit validation
QSAR Modeling
- Curate activity data (ChEMBL IC50/Ki/EC50)
- Calculate molecular descriptors (RDKit)
- Feature selection
- Model training (Random Forest, XGBoost, neural network)
- Validation (cross-validation, external test set)
- Applicability domain assessment
Molecular Property Prediction
- Lipophilicity (LogP)
- Solubility (LogS)
- Permeability (PAMPA, Caco-2)
- Metabolic stability (CYP inhibition)
- hERG toxicity
- BBB penetration
Databases
| Database | Content | Access |
|---|---|---|
| PubChem | 100M+ compounds | Free API |
| ChEMBL | Bioactivity data | Free API |
| PDB | 200K+ protein structures | Free API |
| ZINC | Purchasable compounds | Free download |
| DrugBank | Drug information | Free academic |
| Materials Project | Inorganic materials | Free API |
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.
- 11d ago First seen · 55 lines · 2 tokens per session scan A 5236af415cd2
chemistry is a skill published in the GitHub repository beita6969/ScienceClaw (898 stars, last pushed 3mo ago), licensed MIT. It adds 2 tokens to every session and 434 once invoked, about $0.0000 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
structure-prediction
Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.
saelens
Train sparse autoencoders to interpret model features.
bulk-rnaseq
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and…
esm
Use when working directly with the esm Python SDK, ESM3 or ESMC model IDs, Forge/Biohub inference clients, or ESMFold2 folding workflows.
genomic-intelligence
Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (keyless public demo): promoter regions, splice donor/acceptor sites, enhancer…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.