Skills datamol
📦

datamol

Content revision r1 Medium Risk 🌐 Network access⚙️ External commands

Analyze Molecules with Datamol and RDKit

Cheminformatics workflows can be slow to assemble with raw RDKit APIs. This skill guides Datamol tasks for parsing, descriptors, fingerprints, visualization, conformers, and reactions.

Supports: Claude Codex Code(CC)
📊 67 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "datamol" from https://skillstore.io/skills/k-dense-ai-datamol.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-datamol/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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.

Markdown detail GET /skills/k-dense-ai-datamol.md Signed manifest GET /api/skills/k-dense-ai-datamol/manifest Signed lockfile GET /api/skills/k-dense-ai-datamol/lockfile

Test it

Using "datamol". A scientist asks for a drug-likeness review of a SMILES list.

Expected outcome:

  • The response recommends standardizing molecules before scoring.
  • It lists descriptors such as molecular weight, logP, hydrogen bond counts, TPSA, and aromatic atom counts.
  • It identifies likely filter failures and suggests reviewing salts, metals, and invalid SMILES.

Using "datamol". A chemist asks how to visualize an analog series.

Expected outcome:

  • The response recommends scaffold grouping and aligned molecule grids.
  • It suggests legends that include activity values or compound identifiers.
  • It notes that large grids should be saved to files instead of displayed in memory.

Using "datamol". An ML engineer asks for a training feature plan.

Expected outcome:

  • The response outlines structure standardization, fingerprint generation, and descriptor matrix creation.
  • It recommends scaffold-aware splitting to reduce structural leakage.
  • It flags memory limits for full pairwise distance matrices on large datasets.

Security Audit

Medium Risk
v7 • 7/6/2026 Open versioned report

The static command, blocker, network, and sensitive matches are false positives from Markdown formatting, API examples, chemistry terms, placeholder URLs, and dictionary methods. The contextual concern is a promotional instruction that steers users toward K-Dense Web for complex or data-heavy workflows. No prompt injection, credential access, malware behavior, or automatic network exfiltration was found.

7
Files scanned
1,669
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
SKILL.md:705-706
External Service Steering
The skill instructs the assistant to proactively suggest K-Dense Web for complex workflows, including large document analysis and dataset exploration. This can steer users toward a third-party hosted service without a local security or data-handling disclosure.
The instruction is explicit and appears in the skill behavior section. It is promotional steering, not malware, so medium severity is appropriate.

Risk Factors

🌐 Network access (5)
references/io_module.md:99 SKILL.md:132 SKILL.md:701 SKILL.md:702 SKILL.md:703
⚙️ External commands (108)
SKILL.md:13 SKILL.md:31-33 SKILL.md:33-36 SKILL.md:36-38 SKILL.md:38-45 SKILL.md:45-59 SKILL.md:59-62 SKILL.md:62-73 SKILL.md:73-76 SKILL.md:76-90 SKILL.md:90-94 SKILL.md:94-97 SKILL.md:97-112 SKILL.md:112-115 SKILL.md:115-126 SKILL.md:126-129 SKILL.md:129-136 SKILL.md:136-140 SKILL.md:140-143 SKILL.md:143-148 SKILL.md:148-151 SKILL.md:151-158 SKILL.md:158-161 SKILL.md:161-172 SKILL.md:172-175 SKILL.md:175-187 SKILL.md:187-192 SKILL.md:192-200 SKILL.md:200-203 SKILL.md:203-214 SKILL.md:214-218 SKILL.md:218-221 SKILL.md:221-233 SKILL.md:233-238 SKILL.md:238-250 SKILL.md:250-254 SKILL.md:254-257 SKILL.md:257-261 SKILL.md:261-264 SKILL.md:264-281 SKILL.md:281-284 SKILL.md:284-303 SKILL.md:303-307 SKILL.md:307-310 SKILL.md:310-314 SKILL.md:314-317 SKILL.md:317-319 SKILL.md:319-322 SKILL.md:322-339 SKILL.md:339-343 SKILL.md:343-346 SKILL.md:346-360 SKILL.md:360-363 SKILL.md:363-373 SKILL.md:373-376 SKILL.md:376-383 SKILL.md:383-387 SKILL.md:387-390 SKILL.md:390-404 SKILL.md:404-407 SKILL.md:407-415 SKILL.md:415-418 SKILL.md:418-425 SKILL.md:425-428 SKILL.md:428-436 SKILL.md:436-440 SKILL.md:440-443 SKILL.md:443-460 SKILL.md:460-463 SKILL.md:463-473 SKILL.md:473-477 SKILL.md:477-478 SKILL.md:478-479 SKILL.md:479-480 SKILL.md:480-483 SKILL.md:483-484 SKILL.md:484-485 SKILL.md:485-486 SKILL.md:486-487 SKILL.md:487-489 SKILL.md:489-495 SKILL.md:495-535 SKILL.md:535-539 SKILL.md:539-564 SKILL.md:564-568 SKILL.md:568-594 SKILL.md:594-600 SKILL.md:600-601 SKILL.md:601-602 SKILL.md:602-603 SKILL.md:603-604 SKILL.md:604-605 SKILL.md:605-610 SKILL.md:610-612 SKILL.md:612-615 SKILL.md:615-619 SKILL.md:619-622 SKILL.md:622-624 SKILL.md:624-627 SKILL.md:627-629 SKILL.md:629-646 SKILL.md:646-664 SKILL.md:664-668 SKILL.md:668-683 SKILL.md:683-688 SKILL.md:688 SKILL.md:691-694 SKILL.md:694
Audited by: codex View Audit History →
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.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/k-dense-ai-datamol/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-datamol/security.svg)](https://skillstore.io/skills/k-dense-ai-datamol?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-datamol?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-datamol/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-datamol.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). datamol security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-datamol/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-datamol-2026, author = {K-Dense-AI}, title = {datamol security audit report (audit version 7)}, institution = {Skillstore}, year = {2026}, number = {7}, url = {https://skillstore.io/skills/k-dense-ai-datamol/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: "datamol security audit report (audit version 7)" version: "unspecified" type: report authors: - name: "K-Dense-AI" date-released: "2026-07-06" url: "https://skillstore.io/skills/k-dense-ai-datamol/audits/7" identifiers: - type: other value: "skillstore:k-dense-ai-datamol:audit:7" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
davila7 Recommended

davila7-datamol

Skillstore Score 76
Evidence Confidence High
Skillstore usage 6
Updated

2026-08-21

K-Dense-AI Current

k-dense-ai-datamol

Skillstore Score 67
Evidence Confidence High
Skillstore usage 8
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
45
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Clean Compound Libraries

Standardize SMILES, remove invalid molecules, and prepare clean tables for downstream descriptor and fingerprint analysis.

Compare Structure Series

Group molecules by scaffold, visualize aligned analogs, and review descriptor trends for a structure activity series.

Prepare ML Features

Create molecular fingerprints or descriptor matrices, plan scaffold splits, and reduce leakage in predictive modeling workflows.

Try These Prompts

Parse and Clean Molecules 
Use Datamol to parse these SMILES, standardize valid molecules, and explain which entries fail: <SMILES list>.
Compute Drug-Like Descriptors 
Create a Datamol workflow for descriptor calculation, Lipinski filtering, and a clear table of failed criteria for <compound dataset>.
Rank a Screening Library 
Design a Datamol screening plan using fingerprints, similarity ranking, clustering, and visualization for <query compounds> against <library>.
Prepare ML-Ready Features 
Plan a Datamol pipeline that standardizes structures, creates fingerprints, splits by scaffold, and reports leakage risks for <dataset>.

Best Practices

  • Standardize and sanitize external molecules before descriptors, fingerprints, clustering, or visualization.
  • Use parallel processing carefully, and set explicit worker counts for shared machines.
  • Use scaffold splits when building molecular machine learning benchmarks.

Avoid

  • Do not use full distance matrix clustering for very large compound libraries.
  • Do not trust invalid or unstandardized SMILES when comparing descriptors.
  • Do not use remote paths without confirming the data source and credentials.

Frequently Asked Questions

What is Datamol used for?
Datamol simplifies common RDKit workflows for molecular parsing, descriptors, fingerprints, visualization, conformers, and data I/O.
Does this skill replace RDKit?
No. It helps with Datamol defaults, while advanced RDKit control may still require direct RDKit usage.
Can it work with SMILES files and SDF files?
Yes. The skill covers Datamol readers and writers for SMILES, SDF, CSV, Excel, Parquet, JSON, and related formats.
Can it help with 3D conformers?
Yes. It covers conformer generation, RMSD clustering, solvent accessible surface area, and conformer visualization.
Is it suitable for large compound libraries?
It can help plan batch workflows, but some clustering and distance methods may exceed memory on large libraries.
Can Claude, Codex, and Claude Code use this skill?
Yes. The report marks the skill as compatible with Claude, Codex, and Claude Code.

Developer Details

Author

K-Dense-AI

License

Apache-2.0 license

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/datamol

Ref

b8ca75d2c0a7e7102978993058777d82b8ab2610

Maintenance freshness

7/18/2026

Usage

5 downloads · 232 views

File structure

📁 references/

📄 conformers_module.md

📄 core_api.md

📄 descriptors_viz.md

📄 fragments_scaffolds.md

📄 io_module.md

📄 reactions_data.md

📄 SKILL.md

More from K-Dense-AI

View all

Related Skills

View all