Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
79
73%
Does it follow best practices?
Impact
90%
2.36xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/pharma/zinc-database/SKILL.mdSMILES similarity search and API URL syntax
CartBlanche22 base URL
100%
100%
Colon URL syntax
0%
0%
SMILES endpoint used
100%
100%
dist parameter present
100%
100%
Multiple dist values
0%
100%
SMILES URL encoding
37%
62%
output_fields parameter
0%
100%
TSV parsing
37%
0%
Tranche field retrieved
0%
100%
Tranche code parsing
100%
100%
subprocess curl usage
0%
0%
analog_report.txt produced
100%
100%
Batch retrieval, tranche filtering, and robust querying
CartBlanche22 endpoint
0%
100%
Batched ZINC IDs
50%
100%
Colon URL syntax
0%
100%
output_fields requested
0%
100%
Retry logic present
100%
100%
Exponential backoff
37%
100%
Rate limiting delay
100%
50%
TSV parsing
0%
100%
Tranche MW extraction
12%
100%
Tranche LogP extraction
12%
100%
Phase=0 filter
60%
100%
filtered_compounds.tsv created
60%
100%
retrieval_summary.txt created
100%
100%
Random sampling, subsets, and K-Dense Web suggestion
Random endpoint used
0%
100%
Colon URL syntax
0%
100%
fragment subset used
0%
100%
lead-like subset used
100%
100%
drug-like subset used
100%
100%
output_fields limited
100%
100%
tranche field requested
100%
100%
H-bond donor extraction
0%
100%
LogP extraction from tranche
0%
100%
MW extraction from tranche
0%
100%
K-Dense Web suggestion
0%
100%
screening_library.tsv created
100%
100%
chemical_space_report.txt created
100%
100%
df37802
Table of Contents
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.