recall

Solid

Semantic recall across the agent's full knowledge base via the vector_brain index (knowledge-graph pages, knowledge files, memory, reviewed outputs, persona memory). Trigger whenever the user asks 'what do we have on X', 'find me info about Y', 'search memory for Z', 'do we have a note on W', 'recall X', 'remember anything about Y', 'what do I know about Z', or whenever the current conversation needs grounding against prior work you don't have in active context. Use this BEFORE guessing or saying 'I don't have context on that'. the vector brain likely does. Returns ranked semantic matches with similarity scores.

AI & Automation 3 stars 0 forks Updated today MIT

Install

View on GitHub

Quality Score: 79/100

Stars 20%
20
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# 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...

Details

Author
0xUrsanomics
Repository
0xUrsanomics/utopia-os
Created
5 days ago
Last Updated
today
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category