stanislavjiricek/phase-output
skills/phase-output/SKILL.md
Phase guidance for the neuroflow /output command. Orients agent approach for outputting project memory or the whole project safely and with correct exclusions.
$ install --global
skillsauthnpx skillsauth add stanislavjiricek/neuroflow phase-outputInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 14, 2026, 11:55 PM1.5s1 file scanned
SKILL.md
- name:
- phase-output
- description:
- Phase guidance for the neuroflow /output command. Orients agent approach for outputting project memory or the whole project safely and with correct exclusions.
phase-output
The /output command packages and moves project data out of the workspace. Its job is to give the user a clean, portable snapshot without accidentally including sensitive files.
Approach
- Clarify the user's intent before choosing scope — "sharing with a collaborator" suggests memory-only; "handing off the full repo" suggests whole project
- Always exclude
sessions/(local-only, can be large) andintegrations.json(API credentials — must never be shared) - Prefer zip over folder copy for sharing — it is a single file and preserves timestamps
- Use Python's
zipfilemodule first; fall back to systemzip/taronly if Python is unavailable - If the user asks about Notion integration or other cloud destinations, acknowledge it is planned but not yet implemented — offer zip as the portable alternative for now
- Do not modify the project or
.neuroflow/state during export — the command is read-only except for writing the export log
Scope guidance
| Scope | Best for |
|---|---|
| Project memory (.neuroflow/ minus exclusions) | Sharing context with a collaborator who has their own codebase; supervision meetings; archiving project decisions and reasoning |
| Whole project (git-tracked + .neuroflow/) | Full handoff, long-term archiving, submitting to a data repository |
| Single phase | Focused handoff — e.g. sending only the data-analyze/ memory to a statistician |
Exclusions — always enforce
| Excluded | Reason |
|---|---|
| .neuroflow/sessions/ | Local-only operation log — large, personal, not meaningful to external recipients |
| .neuroflow/integrations.json | API credentials (PubMed email, Miro token) — must never leave the local machine |
If the user explicitly asks to include sessions or credentials, explain why that is inadvisable and confirm they still want to before proceeding.
File naming convention
Default names for export outputs:
output-[project-slug]-[YYYY-MM-DD].zip
output-[project-slug]-[YYYY-MM-DD]/ (folder copy)
output-[phase]-[project-slug]-[YYYY-MM-DD].zip (single-phase)
Where project-slug is the project name from project_config.md, lowercased with spaces replaced by hyphens.
What to suggest if the user asks "what else can I export?"
- Manuscript draft — if
paper/exists, offer to run/write-reportto generate a summary first, then include it in the export alongside any manuscript files from thepaperoutput path - Analysis report — run
/write-reportfirst to generate a summary, then include it in the export - Reasoning log — mention that
.neuroflow/reasoning/is included in the memory export and contains all documented decisions
Do not suggest Notion or other cloud integrations — they are not implemented yet.
Relevant skills
neuroflow:neuroflow-core— read first; defines the command lifecycle and.neuroflow/write rulesneuroflow:notebooklm— when the user wants a podcast, infographic, slide deck, or audio summary generated from exported project materials, invoke thenotebooklmskill to create a NotebookLM notebook and feed the exported files into it as sources
Related Skills
stanislavjiricek/bids
testing
VerifiedTrustedCommunity
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.
3SKILL.mdUpdated Jun 5, 2026
stanislavjiricek/phase-meeting
tools
VerifiedTrustedCommunity
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).
3SKILL.mdUpdated Apr 25, 2026
stanislavjiricek/worker-critic
data-ai
VerifiedTrustedCommunity
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.
3SKILL.mdUpdated Apr 14, 2026
stanislavjiricek/wiki
development
VerifiedTrustedCommunity
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).
3SKILL.mdUpdated Apr 14, 2026