brainless-lab

Guide for operating, extending, and interpreting BrainlessLab.jl, the Julia research platform for behaviour from self-organising neural substrates. Use for every task in the brainless-lab repository. Covers CompositionSpec, EvaluationSpec, typed registries, profile, sweep, ablation, evolution, benchmark plans, ExperimentSpec, versioned records, evidence boundaries, and node or task extension. Pair with the Julia skill for language, dispatch, inference, allocation, and package hygiene.

Comprehensive guide for writing, reviewing, debugging, and optimizing Julia code for scientific computing — covering type stability, multiple dispatch design, memory and allocations, profiling/debugging tools, package and environment management, parallelism, and the scientific ecosystem (SciML/DifferentialEquations.jl, Agents.jl, DynamicalSystems.jl) relevant to computational neuroscience and artificial-life modeling. Use this skill any time Julia code is being written, generated, reviewed, refactored, explained, or debugged — including diagnosing why Julia code is slow, fixing type instabilities, choosing a package or data structure, setting up a Julia project environment, or reviewing someone else's (or your own previously generated) Julia code for correctness and idiom — even if the request doesn't explicitly mention "performance," "Julia," or this skill by name.