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 sanitization, specialized algorithms.

1.38x

Quality

75%

Does it follow best practices?

Impact

93%

1.38x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/rdkit/SKILL.md

Evaluation results

100%

33%

Virtual Screening for Kinase Inhibitor Analogues

Fingerprint generation and similarity screening

Criteria

Without context

With context

Modern fingerprint API

100%

Morgan radius parameter

100%

Morgan fpSize parameter

100%

Bulk similarity calculation

100%

None check after parsing

100%

Supplier for file reading

100%

titleLine=False for SMILES

100%

Generator GetFingerprint

100%

Results ranked by similarity

100%

Output file written

100%

38%

3D Conformer Generation and Structural Diversity Analysis

3D conformer generation and molecular clustering

Criteria

Without context

With context

AddHs before embedding

100%

ETKDG embedding

100%

randomSeed parameter

30%

100%

Force field optimization

100%

None check after parsing

100%

Morgan generator for clustering

100%

Distance matrix construction

25%

100%

Butina clustering

100%

Cluster results written

100%

3D coords in output

100%

80%

Drug-Likeness Profiling and Scaffold Analysis of a Compound Library

Compound library filtering and descriptor analysis

Criteria

Without context

With context

MolFromSmarts for queries

100%

None check after parsing

100%

DetectChemistryProblems usage

Batch descriptor calculation

Lipinski MW threshold

100%

Lipinski LogP threshold

100%

Lipinski HBD threshold

100%

Lipinski HBA threshold

100%

SDMolSupplier for batch I/O

100%

SDWriter with close

100%

MurckoScaffold analysis

100%

Results report written

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 086de41

Evaluated: about 1 month ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Virtual Screening for Kinase Inhibitor Analogues 3D Conformer Generation and Structural Diversity Analysis Drug-Likeness Profiling and Scaffold Analysis of a Compound Library

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.