Phase brain optimize
Skill stanislavjiricek/neuroflow/skills/phase-brain-optimize
Phase guidance for the neuroflow /brain-optimize command. Loaded automatically when /brain-optimize is invoked to orient agent behavior, relevant skills, and workflow hints for parameter search and model fitting.From its SKILL.md
npx -y skills add stanislavjiricek/neuroflow --skill phase-brain-optimizeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.5 KB, as published. Nobody here has run it
phase-brain-optimize
The brain-optimize phase covers parameter exploration and model fitting — sweeping a parameter space to map model behaviour, or optimising parameters to match experimental data.
Approach
- Identify the goal early: exploratory sweep vs targeted fitting to experimental data
- Write
optimize-plan.mdbefore any code — parameters, bounds, cost function, algorithm, convergence criterion - Always run a minimal smoke test (2–3 evaluations) before launching a full search
- Prefer algorithms suited to the problem: grid search for low-dimensional spaces; differential evolution or Bayesian optimisation for high-dimensional or expensive simulations
Relevant skills
neuroflow:neuroflow-core— read first; defines the command lifecycle and.neuroflow/write rules
Workflow hints
- All optimisation scripts and raw results go to
output_path(models/optimize/), not inside.neuroflow/ - Save
optimize-plan.mdand post-run summaries to.neuroflow/brain-optimize/ - Log algorithm choice and cost function rationale in
.neuroflow/reasoning/brain-optimize.json - Common libraries: DEAP, Optuna, scipy.optimize, BluePyOpt, scikit-optimize
Slash command
/neuroflow:brain-optimize — runs this workflow as a slash command.