agentleFS
Sign inStart free
ArtemXTechArtemXTech/personal-os-skills/skills/granola/SKILL.md

granola

Skill545 starsChanged 54 days agoMITView on GitHub

Query and sync Granola meetings to Obsidian vault. Use when user mentions Granola, meeting transcripts, or wants to sync meeting notes. Reads from local cache - no API needed.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No API calls needed - reads directly from local cache.

    line 17
  2. Very specific:

    Use Granola.base to query synced meetings:

    line 126

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

# List all meetings
python3 .claude/skills/granola/scripts/granola.py list

# Get specific meeting with transcript
python3 .claude/skills/granola/scripts/granola.py get <id>

# Sync new meetings to vault
python3 .claude/skills/granola/scripts/granola.py sync

# Sync specific meeting
python3 .claude/skills/granola/scripts/granola.py sync --id <id>

Commands

list

List all Granola meetings with sync status.

python3 .claude/skills/granola/scripts/granola.py list
python3 .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.

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

sync

Sync meetings to Meetings/ as structured Markdown.

# Sync new meetings only
python3 .claude/skills/granola/scripts/granola.py sync

# Sync specific meeting
python3 .claude/skills/granola/scripts/granola.py sync --id <id>

# Re-sync all (overwrites existing)
python3 .claude/skills/granola/scripts/granola.py sync --all

Output Format

Synced meetings are saved to Meetings/ with this structure:

---
type: granola-meeting
date: 2026-01-09
time: "19:30"
duration_min: 86
granola_id: abc123...
people:
  - "[[Sarah Chen]]"
topics: []
status: raw
---

# Meeting Title

## Notes

(Your notes from Granola)

## Transcript

[19:30:45] 🎤 Hey, how's it going?
[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:

ViewFilter
RecentLast 7 days
Needs Processingstatus = raw
By PersonGrouped by people field

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:

{
  "text": "Hey, how's it going?",
  "source": "microphone",
  "start_timestamp": "2026-01-09T19:30:45.123Z",
  "end_timestamp": "2026-01-09T19:30:48.456Z"
}

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free