recalllisted
Install: claude install-skill 0xUrsanomics/utopia-os
# Recall. Semantic search across the knowledge base
## Brain-First 5-Step Protocol (MANDATORY before external calls)
Adapted from a brain-first convention. Before using ANY external API (web search, a research MCP, a spreadsheet MCP for re-fetch, social APIs, web fetches) to research a person, company, deal, or topic, run all 5 steps below. The brain almost always has something. External APIs fill gaps, not start from scratch.
### The 5 Steps
1. **Keyword search (FTS5/BM25)**: `vector_brain.py search "<name>" --mode bm25 --top 5`. Catches exact-match acronyms, names, deal IDs.
2. **Semantic query (hybrid RRF, default)**: `vector_brain.py search "<natural question about the entity>" --top 5 --expand-window 1`. Catches related context, synonyms, multi-entity questions. `--expand-window 1` attaches the neighbor chunks (↑/↓) of each match so context split across adjacent chunks (date/outcome/caveat) is not lost.
3. **Read the full page**: for the top promising result, use the `Read` tool on the source file path. Don't act on the 200-char preview alone.
4. **Check backlinks**: for entities that have a knowledge-graph page (a person / a prospect / a deal), use your knowledge graph's backlink lookup to see who references it. Surfaces upstream + downstream context.
5. **Check the timeline**: for entities active in deals or schedules, scan the knowledge-graph journal pages for recent mentions, OR grep the journals for the last 14-30 days.
If ALL 5 steps return empty → THEN escala