auto-discovery

name	auto-discovery
description	Discover non-obvious cross-domain connections through random sampling and pattern analysis
automation	autonomous
schedule	0 20 * * 0
allowed-tools	Read, Write, Grep, Glob, Bash

Auto-Discovery

Autonomous cross-domain connection hunter. Samples notes from different thematic clusters and finds meaningful relationships that semantic similarity alone would miss.

Purpose

Find non-obvious, cross-domain connections - notes with low semantic similarity (0.50-0.70) but high conceptual strength. These are the hidden patterns in the knowledge base.

State Dependencies

Source	Location	Read	Write	Description
Permanent Notes	Brain/02-Permanent/	✓		Sampling source
AI Extracted Notes	Brain/AI Extracted Notes/	✓		Sampling source
Document Insights	Brain/Document Insights/	✓		Sampling source
Local Brain Search	resources/local-brain-search/	✓		Similarity scores, connections
Session Changelogs	Brain/05-Meta/Changelogs/		✓	Dated discovery log
Master Changelog	Brain/CHANGELOG.md	✓	✓	Summary entry

Prerequisites

• Local Brain Search index up-to-date (/refresh-index)
• Brain vault accessible

Process

Step 1: Get Current Date

date '+%Y-%m-%d'

Use for changelog filename.

Step 2: Strategic Sampling

Sample from 3-5 diverse domains using Local Brain Search:

# --no-track: autonomous weekly loop; its cross-domain samples must NOT train q-values (scope-primitive learning hygiene).
# BRAIN_READ_SCOPE=<wide>: cross-domain (non-core) sampling is this skill's PURPOSE, so it must read past
#   the core fingerprint. Set it wide rather than letting it fail closed to core once enforcement is on.
#   Only the learn axis is closed (--no-track); the read axis is deliberately wide.
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "dopamine" --limit 5 --no-track --json
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "uncertainty" --limit 5 --no-track --json
BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_search.sh "identity" --limit 5 --no-track --json

Pick seed notes from different clusters.

Step 3: Get Connections for Seeds

For each seed note (same wide read-scope - the seeds and their neighbors live across domains):

BRAIN_READ_SCOPE=core,Books,document-insights,meta,inbox,output resources/local-brain-search/run_connections.sh "Note Name" --json

Identify notes with similarity 0.50-0.70 from DIFFERENT domains.

Step 4: Cross-Domain Analysis

For each cross-domain pair:

1. Read both notes fully
2. Record ACTUAL similarity score from search
3. Analyze for:
   • Shared structural patterns
   • Common mechanisms
   • Meta-principles
   • Paradoxes

Rate conceptual strength (1-5 stars).

Target: Low semantic similarity + high conceptual strength = valuable discovery.

Step 5: Document Discoveries

For each strong connection:

## CROSS-DOMAIN CONNECTION

**Node A**: [[Note X]] (Domain: Neuroscience)
**Node B**: [[Note Y]] (Domain: Economics)
**Semantic Similarity**: 0.63 (actual from search)
**Conceptual Strength**: ⭐⭐⭐⭐⭐

**The Link**: [2-3 sentences explaining WHY they connect]
**Shared Pattern**: [The underlying principle]
**Synthesis Opportunity**: [Potential new note title]

Step 6: Create Dated Changelog

Write to Brain/05-Meta/Changelogs/CHANGELOG - Auto-Discovery Session YYYY-MM-DD.md:

## Auto-Discovery Session: YYYY-MM-DD

### Session Parameters
- Notes sampled: [N] from [X] clusters
- Domains analyzed: [list]

### Discoveries Made
**Strong Connections**: [N]
1. [[A]] ↔ [[B]] - [pattern]

**Meta-Patterns**: [N]
**Consilience Zones**: [N]

### Session Statistics
- Total notes analyzed: [N]
- Non-obvious connections (similarity < 0.70): [N]

Step 7: Update Master Changelog

Add brief summary to Brain/CHANGELOG.md:

## YYYY-MM-DD - Auto-Discovery Session

See: [[CHANGELOG - Auto-Discovery Session YYYY-MM-DD]]
- [N] connections discovered
- [N] meta-patterns identified

Quality Standards

GOOD discoveries:

• Semantic similarity 0.50-0.70
• Clear conceptual link across domains
• "Aha!" factor - non-obvious insight
• Actionable synthesis opportunity

SKIP:

• High similarity (0.85+) - too obvious
• Same domain - not cross-domain
• Already linked in vault

Error Handling

Error	Recovery
Search returns empty	Try different seed terms
All high similarity	Note in changelog, try broader clusters
Index outdated	Run /refresh-index first

Completion Checklist

• Notes sampled from 3+ different clusters
• ACTUAL similarity scores recorded (not estimated)
• Cross-domain connections with conceptual analysis
• Non-obvious discoveries documented (similarity < 0.70)
• Dated changelog created in Brain/05-Meta/Changelogs/
• Master changelog updated with summary