Phase guidance for the neuroflow /brain-run command. Loaded automatically when /brain-run is invoked to orient agent behavior, relevant skills, and workflow hints for running brain model simulations.
From neuroflownpx claudepluginhub stanislavjiricek/neuroflow --plugin neuroflowThis skill uses the workspace's default tool permissions.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
The brain-run phase covers configuring and executing a simulation run — setting duration, time step, inputs, and recording targets, then collecting and sanity-checking outputs.
.neuroflow/brain-build/ before configuring a runrun-config.md first — make run parameters explicit and reproducible.neuroflow/brain-run/ so runs are reproducibleneuroflow:neuroflow-core — read first; defines the command lifecycle and .neuroflow/ write rulesoutput_path (models/results/), not inside .neuroflow/run-config.md and run-summary.md to .neuroflow/brain-run/.neuroflow/reasoning/brain-run.jsonrun_sim.py and save both to output_path/neuroflow:brain-run — runs this workflow as a slash command.