Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.
SkillScore100Maintained
Automatic
◆Research pack
Last verified 8/24/2026
What it changes
Passed 23 of 23 test cases with the skill, and 20 of 23 without it.
Without skill87%
With skill100%
Checks it passed that the model alone missed
Calls sample from cobra.sampling
Specifies n=500 with method='optgp'
Passes the glucose exchange reaction as carbon source
and 1 more in the full report
3 fixed20 passed either way0 still failing0 broke
Pass-rate lift
+13 pp
Tokens
+251%
Agent turns
0%
Response time
-43%
Model gemini-3.6-flashMeasured 8/24/2026v1 · latest is v223 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
I am running a high-throughput screening loop over thousands of parameter variations in a constraint-based metabolic model in Python. In each iteration, I only need to check the numerical maximum biomass growth rate value and do not need the full reaction flux vector. Using standard full optimization in a loop is bottlenecking performance. Write Python code to compute just the objective value as efficiently as possible for each iteration.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses slim_optimize() on the model object rather than optimize()
Missed
Passed
Does not construct a full Solution object during iteration
Passed
Passed
case-01 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md524 lines2 files
COBRApy — Constraint-Based Metabolic Modeling
Overview
COBRApy is a Python package for constraint-based reconstruction and analysis (COBRA) of genome-scale metabolic models. It provides flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockout screens, flux sampling, production envelopes, gapfilling, and media optimization on SBML-format metabolic networks.
When to Use
Predicting microbial growth rates under different nutrient conditions (FBA)
Identifying essential genes or reactions via single and double knockout screens
Determining flux ranges and alternative optimal solutions (FVA)
Sampling feasible flux distributions to characterize metabolic flexibility
Designing minimal growth media or optimizing carbon sources
Computing production envelopes for metabolic engineering targets
Gapfilling incomplete draft models using a universal reaction database
For kinetic modeling or dynamic ODE-based models, use Tellurium instead
For pathway visualization on metabolic maps, use Escher instead
Optional solvers: CPLEX or Gurobi (faster for large models, require license)
Data: SBML (.xml), JSON, or YAML metabolic model files; available from BiGG Models, AGORA, or ModelSEED
pip install cobra
Pre-flight Interview
Settle these with the user before writing any analysis code.
decisions:
- id: D1
param: modelSource
kind: required
source: user
ask: "Which genome-scale reconstruction, and which version, should be used?"
default: null