drugbank-database

Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.

1.55x

Quality

85%

Does it follow best practices?

Impact

81%

1.55x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

74%

21%

Medication Safety Analysis for Polypharmacy Patients

Polypharmacy interaction network analysis

Criteria

Without context

With context

uv pip install

drugbank-downloader package

100%

Credential env vars

100%

50%

Version specified

XML namespace defined

100%

Bidirectional interaction check

70%

100%

NetworkX graph

100%

Severity keyword classification

60%

100%

Severity weights 3/2/1

100%

Pairwise polypharmacy check

57%

100%

Risk score output

100%

lxml installed

94%

35%

Drug Candidate Similarity Screening and Drug-Likeness Assessment

Chemical similarity search and drug-likeness screening

Criteria

Without context

With context

uv pip install

100%

rdkit import

100%

drugbank-downloader usage

100%

Morgan fingerprint radius=2

70%

100%

Morgan fingerprint nBits=2048

80%

100%

Tanimoto similarity

100%

Similarity threshold ≥0.7

Lipinski MW≤500 and logP≤5

100%

Lipinski HBD≤5 and HBA≤10

100%

Lipinski 1-violation allowance

100%

Veber PSA≤140

100%

Veber rotatable bonds≤10

100%

RDKit structure validation

100%

77%

31%

Drug Repurposing Candidate Discovery via Target Profile Analysis

Target-based drug repurposing with CYP450 and pathway profiling

Criteria

Without context

With context

uv pip install

drugbank-downloader import

100%

Credential env vars

55%

Version specified

UniProt ID matching

100%

Action types extracted

100%

Known-action distinction

100%

CYP450 by gene prefix

40%

100%

SMPDB IDs in pathways

100%

Overlap ratio calculation

70%

100%

Sort by overlap ratio descending

62%

50%

Caching implemented

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 71add64

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Medication Safety Analysis for Polypharmacy Patients Drug Candidate Similarity Screening and Drug-Likeness Assessment Drug Repurposing Candidate Discovery via Target Profile Analysis

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.