Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →matlab/matlab-fit-simbiology-model
Fit SimBiology model parameters to data — fitproblem, population NLME, virtual patients, and NCA.
Passed 19 of 19 test cases with the skill, and 10 of 19 without it.
and 14 more in the full report
11 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am assembling a fit problem object in SimBiology. I need to assign a model `m`, data `gData`, estimated info `eInfo`, dosing array `doses`, and search algorithm `'scattersearch'`. Write the property assignment statements for this object.
| Checked | Without skill | With skill |
|---|---|---|
| The property assignment uses prob.Estimated for the parameter specification object. | Missed | Passed |
| The property assignment uses prob.Doses for the dosing array. | Missed | Passed |
| The property assignment uses prob.FunctionName for the search algorithm. | Missed | Passed |
The instructions your model reads when the skill loads.
Estimate parameters from data using fitproblem, fit population models
with NLME, generate virtual patients, and compute NCA metrics.
matlab-build-simbiology-model)matlab-simulate-simbiology-model)matlab-simulate-simbiology-model)fitproblem for parameter estimationAlways use fitproblem instead of calling sbiofit or sbiofitmixed
directly. fitproblem provides a unified, declarative interface:
prob = fitproblem;
prob.Model = model;
prob.Data = data;
prob.ResponseMap = "Species = DataColumn";
prob.Estimated = estimatedInfo({'param'}, 'Bounds', [lo hi]);
results = fit(prob);
Do NOT call sbiofit(model, data, ...) or sbiofitmixed(model, data, ...)
directly — their positional argument signatures are error-prone.
groupedData, NOT a plain tableAlways wrap data:
test cases passed, vs 10 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.