vault-daydream

Finds hidden connections between your notes by randomly pairing them and spotting patterns, like how your brain makes creative leaps while daydreaming.

Installation
Run `npx skills add "https://github.com/robertbirek/opencode-skills-registry" --skill "vault-daydream"` to install this skill, then follow its SKILL.md instructions for my next request.

Paste this into Claude Code, Cursor, or any agent that can run commands.

SKILL.mdShow the author's original SKILL.md
---
name: vault-daydream
description: Multi-agent system that mines an Obsidian vault for non-obvious connections between notes, mimicking the brain's default mode network. Samples random note pairs, synthesizes connections via Sonnet, filters with Haiku critic. Inspired by Gwern's LLM Daydreaming.
---

# Vault Daydream Skill

Multi-agent system that mines the Obsidian vault for non-obvious connections between notes, mimicking the brain's default mode network. Samples random note pairs, synthesizes connections via Sonnet, filters with Haiku critic.

Inspired by [Gwern's LLM Daydreaming](https://gwern.net/ai-daydreaming).

## Usage

```
/daydream
```

## What it does

1. Auto-detects vault root from current directory (asks if not found)
2. Scans vault for notes modified in last 120 days
3. Generates 50 recency-weighted random pairs
4. Synthesizes connections (Sonnet, parallel batches of 5)
5. Critiques and scores insights (Haiku, parallel batches)
6. Filters for quality (average score >= 7.0)
7. Saves insight notes to `Daydreams/` folder
8. Generates daily digest in `Daydreams/digests/`
9. Appends summary to today's daily note

## Output

- **Individual insights**: `Daydreams/YYYYMMDD-slug.md` -- full synthesis with scores and wikilinks
- **Daily digest**: `Daydreams/digests/YYYYMMDD-digest.md` -- stats + ranked top insights
- **Daily note**: Summary appended under `## Daydream`
- **History log**: `ai-research/daydream/history.json` -- tracks sampled pairs for dedup

## Architecture

```
Skill (orchestrator)
  |-- Glob/Read: scan vault, extract excerpts
  |-- Generate 50 random pairs (recency-weighted)
  |-- Task(model: sonnet) x 10: synthesize connections  <-- parallel
  |-- Task(model: haiku) x 10: critique/score insights  <-- parallel
  |-- Filter (avg >= 7.0)
  +-- Write: save insight notes + daily digest
```

No external dependencies -- pure native tools (Glob, Read, Write, Bash, Task).

## Cost

Per run (~50 pairs): approximately $0.40-0.50 via Claude Code usage.

Mirrored from the author's public source. Install counts from the open skills registry.

The systems behind these skills get built for partners every week.

Partner with us