medchem
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
65
58%
Does it follow best practices?
Impact
63%
3.50xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/medchem/SKILL.mdEvaluation results
100%
65%Virtual Compound Library Screening for Oral Drug Discovery
Multi-rule compound library triage
medchem import
0%
100%
datamol for SMILES conversion
0%
100%
RuleFilters class used
0%
100%
Multiple rules in RuleFilters
0%
100%
Parallelization enabled
0%
100%
CommonAlertsFilters used
0%
100%
Results combined
100%
100%
Filtered compounds saved
100%
100%
Filtering decisions documented
100%
100%
47%
30%CNS Compound Prioritization for Alzheimer's Disease Program
CNS drug filtering with constraints and query language
medchem import
0%
100%
datamol used
0%
0%
rule_of_cns applied
0%
100%
CNS constraints values
0%
33%
ComplexityFilter applied
0%
50%
Complexity threshold
0%
0%
Query language used
0%
0%
Parallelization
0%
0%
CNS candidates output
100%
100%
Filtering summary
100%
100%
43%
40%Lead Compound Prioritization for Kinase Inhibitor Program
Lead optimization structural alert analysis
medchem import
0%
100%
datamol used
0%
0%
NIBRFilters applied
0%
100%
LillyDemeritsFilters applied
0%
0%
Lilly rejection threshold
0%
0%
rule_of_leadlike_strict applied
0%
0%
ComplexityFilter threshold
0%
40%
ChemicalGroup detection
0%
100%
n_jobs=-1 parallelization
0%
0%
Prioritized compounds output
25%
58%
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
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.