skills/phase-ideation/SKILL.md
Phase guidance for the neuroflow /ideation command. Loaded automatically when /ideation is invoked to orient agent behavior, relevant skills, and workflow hints for the ideation phase.
npx skillsauth add stanislavjiricek/neuroflow phase-ideationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
The ideation phase is the entry point of a research project — sharpening a vague idea into a testable research question and mapping the existing literature rigorously.
skills/phase-ideation/references/search-protocol.md — do NOT spawn sub-agents.md metadata stubs for all results and ask the user which papers to downloadliterature-review agent to run the full 12-protocol analysis.md stubs — full download is not requiredproject_config.md already has a research question, confirm whether to refine or restartliterature-review — runs 12 sequential analytical protocols on downloaded papers through the worker-critic loop; produces a compiled literature review saved to .neuroflow/ideation/literature-review-[date].mdcritic — evaluates each protocol output in the literature-review looporchestrator — manages the worker-critic loop when invokedNote: Literature searches are performed inline by the main agent following the search protocol — the
scholaragent is NOT spawned as a sub-agent. Use the standalonescholaragent only for ad-hoc searches outside the/ideationworkflow.
neuroflow:neuroflow-core — read first; defines the command lifecycle and .neuroflow/ write rulesneuroflow:pupil-labs-neon-realtime — if the project involves Pupil Labs Neon eye-tracking hardware, use this skill for real-time data collection and device connection during ideation/piloting.neuroflow/ideation/research-question.mdproject_config.md if the research question is defined or changed.neuroflow/ideation/papers/ — this folder is the input for the literature-review agentliterature-review-[date].md) feeds directly into the paper phase; reference it thereskills/phase-ideation/references/journal-defaults.md to match the query to one of eight neuroscience areas and surface high-impact journals. If the user has custom journal preferences, they can create .neuroflow/journal-preferences.md from the template at skills/phase-ideation/references/user-journal-preferences.md./neuroflow:ideation — runs this workflow as a slash command.
testing
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.
tools
Phase guidance for the /meeting command. Covers meeting file structure, recurring templates, attendee resolution from profiles, Google Calendar MCP integration, agenda preparation with project context, and action-item-to-task conversion at all three levels (project, flowie, hive).
data-ai
Worker-critic agentic loop protocol — orchestrator coordinates a worker agent and a critic agent across up to 3 revision cycles to produce a vetted output for any phase.
development
Knowledge base skill — Karpathy-style LLM-maintained wiki at three levels (personal/flowie, project, team/hive). Handles ingest, query, lint, schema, and project-tagging workflows. Invoked by /flowie --wiki-* (personal), /wiki (project), /hive --wiki-* (team).