neuroflow

Infinite improvement loop for any research artifact — one managing agent makes a focused change each iteration, judges it against the current best, keeps or reverts. Its memory is a per-loop wiki it reads before and writes after every move. Folder lives next to the artifact; never stops until interrupted.

Assemble a computational brain model or continue working on one — neuron models, network topology, connectivity, and simulation framework setup.

Run a parameter search or fit a computational brain model to experimental data.

Run a computational brain model simulation — configure run parameters, launch the simulation, and collect outputs.

Run an analysis pipeline on preprocessed data — ERPs, time-frequency, connectivity, decoding, GLM, or other modality-appropriate analyses.

Autoresearch loop agent — the single managing agent that runs the infinite improvement loop for any phase. Makes one focused change per iteration and judges it itself (no worker/evaluator fan-out), keeping or reverting against the current best. Its memory is a per-loop wiki it reads before and writes after every move. Never stops until the human interrupts. Inspired by Andrej Karpathy's autoresearch (MIT).

Personal identity agent — reads the user's flowie profile and generates deeply personalized assistance based on their research stances, writing style, methodological preferences, and intellectual fingerprint. Invoked when Claude needs to tailor its output to who the user actually is.

Literature review specialist. Runs 12 sequential analytical lenses on a set of downloaded papers — from landscape mapping to future research agenda — using the worker-critic loop to ensure rigour. Scoped to the ideation phase.

Hyper-critical manuscript reviewer for the unified paper phase. Applies the full six-area neuroflow:review-neuro methodology to every section draft — as if reviewing for Nature Neuroscience or Neuron. Returns [STATUS: APPROVED] or [STATUS: REJECTED] with specific, actionable feedback. Never produces content.

Specialist manuscript writer for the unified paper phase. Drafts neuroscience manuscript sections from upstream project memory, journal guidelines, and analysis results — operates inside a brutal write→critique loop with the paper-critic agent and revises until approved or the loop is exhausted.

Infinite improvement loop for any research artifact in any phase — a single managing agent makes one focused change per iteration, judges it against the previous best, keeps or reverts. Its memory is a per-loop wiki it reads before every move and writes after every move. The loop never stops until the human interrupts it. Inspired by Andrej Karpathy's autoresearch (MIT).

This skill should be used whenever the user mentions BIDS, Brain Imaging Data Structure, BIDS conversion, BIDS validation, BIDS compliance, organizing neuroimaging data, dataset_description.json, participants.tsv, bids-validator, pybids, MNE-BIDS, or asks how to structure EEG/MEG/fMRI/iEEG/PET/DWI data for sharing or preprocessing. Also invoke when the user asks how to name scan files, what sidecar JSON fields are needed, how to set up derivatives/, or how to run fMRIPrep/MRIQC on their dataset. Invoke proactively during /data, /data-preprocess, and /data-analyze phases whenever the dataset structure is relevant to the task at hand.

Remove AI writing signatures from prose. Makes text sound genuinely human-authored — varied rhythm, natural register, no AI tells. Use when drafting, editing, or reviewing any text that needs to read as if a person wrote it.

Core rules and lifecycle for all neuroflow commands and agents. Read this whenever running any neuroflow command to understand the .neuroflow/ folder structure and the required behaviour at the start and end of every command.

Guide for developing and maintaining the neuroflow plugin. Use when adding skills, commands, agents, or hooks to neuroflow, bumping the version, or publishing updates to GitHub.

2 hooks across 1 event