rdkit
Analyze Molecules with RDKit
Cheminformatics work often needs precise molecule parsing, descriptor calculation, and structure search. This skill guides Claude, Codex, and Claude Code through RDKit workflows with focused references and scripts.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "rdkit" from https://skillstore.io/skills/k-dense-ai-rdkit.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-rdkit/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "rdkit". Analyze aspirin with RDKit descriptors.
Expected outcome:
A concise property summary with molecular weight, LogP, TPSA, donors, acceptors, rotatable bonds, and Lipinski status.
Using "rdkit". Find benzene-containing molecules in a SMILES file.
Expected outcome:
A filtering plan that names the SMARTS pattern, expected pass counts, output file, and match report.
Using "rdkit". Compare a query molecule to a small SDF library.
Expected outcome:
A ranked hit list with similarity scores, fingerprint method, threshold, and notes about borderline matches.
Security Audit
High RiskThe static findings are false positives from chemistry notation, Markdown code fences, benign RDKit examples, and user-directed output files. No prompt injection or covert external command behavior was found, but the documentation includes unsafe pickle loading guidance that can become code execution with untrusted files.
Confirmed security concerns (1)
Risk Factors
📁 Filesystem access (6)
⚡ Contains scripts (1)
⚙️ External commands (88)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/k-dense-ai-rdkit/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-rdkit?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-rdkit?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-rdkit/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-rdkit.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
K-Dense-AI. (2026). rdkit security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-rdkit/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-rdkit-2026,
author = {K-Dense-AI},
title = {rdkit security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-rdkit/audits/7},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "rdkit security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
- name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-rdkit/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-rdkit:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
k-dense-ai-rdkit
2026-08-21
davila7-rdkit
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Screen Compound Libraries
Filter molecule files by descriptors, SMARTS patterns, and similarity thresholds.
Prepare Molecular Features
Generate RDKit descriptors and fingerprints for QSAR, clustering, or model input.
Build Chemistry Workflows
Adapt RDKit examples into local scripts for parsing, visualization, and batch processing.
Try These Prompts
Use RDKit to analyze this SMILES string: CCO. Report molecular weight, LogP, TPSA, donors, and acceptors.
Create an RDKit plan to filter molecules.smi for benzene rings and exclude acyl chlorides. Include expected output files.
Use Morgan fingerprints to compare a query SMILES against database.sdf. Explain threshold choice and result ranking.
Design an RDKit workflow for library triage using descriptors, PAINS filters, similarity clustering, and molecule images.
Best Practices
- Validate every parsed molecule before calculating descriptors or fingerprints.
- Use streaming suppliers for large SDF files to control memory use.
- Record fingerprint type, radius, bit length, and similarity metric with results.
Avoid
- Do not use descriptor outputs as experimental proof without expert review.
- Do not load pickled molecule files from untrusted sources.
- Do not share mutable MolSupplier objects across worker threads.
Frequently Asked Questions
What is this skill best for?
Does it install RDKit?
Can it process SDF and SMILES files?
Can it generate molecule images?
Is it suitable for drug discovery workflows?
Does it send molecule data to external services?
Developer Details
Author
K-Dense-AILicense
BSD-3-Clause license
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
7 downloads · 603 views
File structure