stanislavjiricek/phase-search
skills/phase-search/SKILL.md
Lightweight search skill for the /search command. Instructs the agent to use flow.md files as a fast index, scope the search by tag (project or memory), and return a concise summary to the main agent.
$ install --global
skillsauthnpx skillsauth add stanislavjiricek/neuroflow phase-searchInstall 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, 2:11 AM13.4s1 file scanned
SKILL.md
- name:
- phase-search
- description:
- Lightweight search skill for the /search command. Instructs the agent to use flow.md files as a fast index, scope the search by tag (project or memory), and return a concise summary to the main agent.
phase-search
Fast, minimal search of the project. Use this skill when running /search. Do not do deep exploration — read the index first, search only what is needed, and return a brief summary.
Tag-based scoping
Every search invocation carries a scope tag. Recognise these two tags:
| Tag | Scope | What to search |
|---|---|---|
| memory | Inside .neuroflow/ only | All .neuroflow/ files: project_config.md, flow.md, phase subfolders, sessions, reasoning |
| project | Outside .neuroflow/ | Source files, scripts, notebooks, data files, config files in the repo root and subdirectories — everything except .neuroflow/ |
If no tag is provided, default to memory and inform the user.
Search strategy — use flow.md as the index
For memory searches
- Read
.neuroflow/flow.md— this is the root index. Note which phase subfolders exist and their descriptions. - For each phase subfolder relevant to the query, read its
flow.md— this lists the files and their one-line descriptions. - If the query term appears in a description or filename in the index, open that specific file for a targeted read.
- Only read the full content of files that the index points to as relevant — do not read every file.
For project searches
- Read
.neuroflow/flow.mdfirst — it listsoutput_pathvalues for each phase, pointing to where scripts, results, and manuscripts live. - Use the
output_pathentries to quickly locate the relevant directories. - Search those directories for files matching the query (by filename or targeted content search).
- Do not recurse into directories that are clearly unrelated.
Response format
Return a compact summary, not a full report. Structure:
🔍 Search: "<query>" [scope: memory | project]
Found in:
• <file-path> — <one-line reason why it matches>
• <file-path> — <one-line reason why it matches>
Summary: <2–4 sentences synthesising what was found>
If nothing is found:
🔍 Search: "<query>" [scope: memory | project]
No matches found. Checked: <list of flow.md files consulted>
Suggestion: <one-line suggestion — try a different tag, different term, or check if the phase has been started>
Rules
- Be fast: consult the flow.md index before opening any other file. Never open a file that the index does not point to as relevant.
- Be brief: the summary is for the main agent, not the user. Keep it to the essential finding.
- Do not modify anything: this skill is read-only. Never write to
.neuroflow/or any project file. - Do not recurse blindly: if the query matches nothing in the flow.md indices, report not-found rather than scanning all files.
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