Guidance for deep knowledge graph traversal across Brain memory notes, entities, and relationships. Use when needing comprehensive context before planning, investigating connections between concepts, or answering "what do you know about X" questions.
Brain stores knowledge as an interconnected graph: notes link to other notes via wikilink relations, observations capture categorized facts, and semantic search with depth traversal reveals context that simple queries miss.
| Trigger Phrase | Operation |
|---|---|
what do you know about X | Full knowledge graph traversal |
how do I explore the knowledge graph | Graph exploration workflow |
how are these concepts connected | Relation traversal via depth parameter |
give me comprehensive context on X | Deep multi-phase exploration |
map out related knowledge for X | Note discovery and relation linking |
Explore the knowledge graph when:
Track visited note identifiers to prevent cycles. Execute phases sequentially.
mcp__plugin_brain_brain__search({
"query": "<topic>",
"mode": "semantic",
"limit": 10
})
Collect: primary note results with titles, permalinks, and content previews.
For key notes from Phase 1, get full content including observations and relations:
mcp__plugin_brain_brain__read_note({
"identifier": "<note title or permalink>"
})
Extract: observations (categorized facts), relations (wikilinks to other notes), tags.
Use the depth parameter to traverse the knowledge graph through relations:
mcp__plugin_brain_brain__search({
"query": "<topic>",
"mode": "semantic",
"depth": 2,
"limit": 10
})
Depth levels:
depth: 1 - Direct relations (1-hop connections)depth: 2 - Relations of relations (2-hop connections)depth: 3 - Deep traversal (3-hop connections, use sparingly)Discover related notes by browsing semantic folders:
mcp__plugin_brain_brain__list_directory({
"dir_name": "decisions",
"depth": 2
})
Key folders to explore: decisions/, analysis/, sessions/, specs/, planning/, skills/
Group findings by type and present structured results.
Group findings by type:
Notes: Primary (direct matches) -> Related (via depth traversal) -> Folder-discovered
Observations: Key facts, decisions, and insights extracted from notes
Relations: Wikilink connections between notes showing how concepts relate
Graph Summary: Total notes found, key themes, relation patterns, suggested follow-up queries
Match depth to task complexity. Start shallow, go deeper if context insufficient.
Use this skill when:
Use curating-memories instead when:
| Avoid | Why | Instead |
|---|---|---|
| Running all 5 phases for simple queries | Wastes tokens on unnecessary traversal | Start shallow (phases 1-2), go deeper only if needed |
| Not tracking visited identifiers | Causes infinite cycles in graph traversal | Maintain a visited set, skip already-seen notes |
| Using depth:3 on broad queries | Exponential blowup on dense graphs | Start with depth:1, increase only if needed |
| Skipping folder discovery when notes reference unknown entities | Misses cross-domain connections | Check list_directory for related folders |
| Presenting raw results without grouping | Overwhelming and unstructured | Group by type: notes, observations, relations |
After graph exploration:
depth: 1 and increase only if neededfolder parameter to scope searches to specific domains