BRENDA Enzyme DB SOAP/REST queries: kinetic parameters (Km, Vmax, kcat, Ki), EC classes, substrate specificity, inhibitors, cofactors, organism data. 80K+ enzymes, 7M+ values. Free academic registration. For metabolic modeling use cobrapy-metabolic-modeling; metabolites use hmdb-database.
SkillScore82Maintained
Automatic
◆Research pack
Last verified 8/28/2026
What it changes
Passed 17 of 21 test cases with the skill, and 10 of 21 without it.
Without skill45%
With skill82%
Checks it passed that the model alone missed
calls the getEcNumber method
specifies a sleep duration of 0.5 to 1 second
identifies the uniprotAccessionNumber property
and 8 more in the full report
8 fixed10 passed either way4 still failing0 broke
Pass-rate lift
+36 pp
Tokens
+170%
Agent turns
0%
Response time
-26%
Model gemini-3.6-flashMeasured 8/28/2026v118 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
After calling the BRENDA API to map an EC number to its UniProt entries, I need to print the accession identifier and the species for each record. What exact property names on the zeep result object contain these two pieces of data?
What was checked, without and with the skill
Checked
Without skill
With skill
identifies the uniprotAccessionNumber property
Missed
Passed
identifies the organism property
Passed
Passed
case-16 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md486 linessingle file
BRENDA Enzyme Database
Overview
BRENDA (BRaunschweig ENzyme DAtabase) is the world's most comprehensive enzyme information system, containing 80,000+ enzyme entries covering all classified enzymes (EC numbers). It holds 7M+ experimentally measured kinetic parameters (Km, Vmax, kcat, Ki, inhibition constants), substrate specificity data, cofactor requirements, tissue expression, and organism-specific enzyme variants from 200,000+ literature references. Programmatic access is via a SOAP-based web service (Python zeep library) with free academic registration.
When to Use
Retrieving kinetic parameters (Km, kcat, Vmax, Ki) for a specific enzyme and substrate combination
Comparing kinetic parameters across organisms or mutant variants for an enzyme
Finding natural substrates, inhibitors, and cofactors for an EC number
Building kinetic models for metabolic simulations requiring Michaelis-Menten parameters
Identifying enzyme-specific structural data (recommended pH, temperature optima)
Cross-referencing EC numbers with UniProt accessions and organism taxonomy
For metabolic network simulation use cobrapy-metabolic-modeling; for metabolite structures use hmdb-database