Granola Skill

Query and sync Granola AI meeting notes to Obsidian vault.

How It Works

Granola stores everything locally at ~/Library/Application Support/Granola/cache-v3.json:

• Documents (meetings with title, notes, people)
• Transcripts (real-time, with timestamps and source)
• Updates in real-time as you record

No API calls needed - reads directly from local cache.

Quick Start

bash
1# List all meetings
2python3 .claude/skills/granola/scripts/granola.py list
3
4# Get specific meeting with transcript
5python3 .claude/skills/granola/scripts/granola.py get <id>
6
7# Sync new meetings to vault
8python3 .claude/skills/granola/scripts/granola.py sync
9
10# Sync specific meeting
11python3 .claude/skills/granola/scripts/granola.py sync --id <id>

Commands

list

List all Granola meetings with sync status.

bash
1python3 .claude/skills/granola/scripts/granola.py list
2python3 .claude/skills/granola/scripts/granola.py list --limit 5

Output:

[✓] 2026-01-09  Team Sync - Weekly
    ID: abc123...
    Transcript: 450 segments, ~86 min

[ ] 2026-01-10  Team Standup
    ID: def456...
    Transcript: 120 segments, ~15 min

• [✓] = already synced to vault
• [ ] = not synced yet

get

View full meeting details and transcript.

bash
1python3 .claude/skills/granola/scripts/granola.py get <id>
2python3 .claude/skills/granola/scripts/granola.py get <id> --no-transcript

sync

Sync meetings to Meetings/ as structured Markdown.

bash
1# Sync new meetings only
2python3 .claude/skills/granola/scripts/granola.py sync
3
4# Sync specific meeting
5python3 .claude/skills/granola/scripts/granola.py sync --id <id>
6
7# Re-sync all (overwrites existing)
8python3 .claude/skills/granola/scripts/granola.py sync --all

Output Format

Synced meetings are saved to Meetings/ with this structure:

markdown
1---
2type: granola-meeting
3date: 2026-01-09
4time: "19:30"
5duration_min: 86
6granola_id: abc123...
7people:
8  - "[[Sarah Chen]]"
9topics: []
10status: raw
11---
12
13# Meeting Title
14
15## Notes
16
17(Your notes from Granola)
18
19## Transcript
20
21[19:30:45] 🎤 Hey, how's it going?
22[19:30:48] 🎤 Great to meet you...

Transcript icons:

• 🎤 = microphone (you)
• 🔊 = system audio (others on call)

Workflow

1. Record meeting in Granola (real-time transcription)
2. Sync to vault: python3 .claude/skills/granola/scripts/granola.py sync
3. Process meeting: Extract action items, update people notes
4. Mark as processed: Change status: raw to status: processed

Querying with Bases

Use Granola.base to query synced meetings:

Data Structure

Local cache: ~/Library/Application Support/Granola/cache-v3.json

cache (JSON string) → state →
  ├── documents: {id: {title, notes_plain, notes_markdown, people, created_at}}
  └── transcripts: {id: [{text, source, start_timestamp, end_timestamp}]}

Transcript segment:

json
1{
2  "text": "Hey, how's it going?",
3  "source": "microphone",
4  "start_timestamp": "2026-01-09T19:30:45.123Z",
5  "end_timestamp": "2026-01-09T19:30:48.456Z"
6}

Tips

• Real-time access: Cache updates as you record - can query mid-meeting
• Free tier hack: Sync hourly to bypass 7-day history limit
• No auth needed: Uses local files, not API