OpenParable
Skip to content
← Back to skills

Granola

Apps & Automation
granola

Granola is an Agent Skill for apps & automation published in the glebis/claude-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

This skill should be used when importing, listing, or exporting Granola meeting recordings and transcripts. Queries Granola's Personal API to list meetings, extract transcripts, and export to Obsidian notes in Fathom-compatible format.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/glebis/claude-skills/blob/HEAD/granola/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/granola, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Granola Meeting Importer

Query Granola via Personal API to list notes, view transcripts, and export to Obsidian vault in the same format as the Fathom skill.

Prerequisites

  • Granola Business or Enterprise plan (Personal API required)
  • API key in sops-encrypted ~/Brains/brain/.env.granola as GRANOLA_API_KEY=grn_...
  • No additional dependencies (uses stdlib only)

Usage

python3 ~/.claude/skills/granola/scripts/granola.py <command> [options]

Commands

CommandDescription
listList notes from Personal API
show <note_id>Show note details (summary, attendees, optionally transcript)
export <note_id>Export note to Obsidian markdown (Fathom-compatible format)

Options

OptionApplies toDescription
--format text|jsonlist, showOutput format (default: text)
--after <ISO date>listFilter notes created after date
--alllistPaginate through all results
--transcriptshowInclude transcript in output
--vault <path>exportObsidian vault path (default: ~/Brains/brain)
--output <path>exportCustom output file path

Examples

List recent meetings

python3 ~/.claude/skills/granola/scripts/granola.py list
python3 ~/.claude/skills/granola/scripts/granola.py list --format json
python3 ~/.claude/skills/granola/scripts/granola.py list --after 2026-05-01

Show note with transcript

python3 ~/.claude/skills/granola/scripts/granola.py show not_5FkswTp4Omkpm5
python3 ~/.claude/skills/granola/scripts/granola.py show not_5FkswTp4Omkpm5 --transcript --format json

Export to Obsidian

python3 ~/.claude/skills/granola/scripts/granola.py export not_5FkswTp4Omkpm5
python3 ~/.claude/skills/granola/scripts/granola.py export not_5FkswTp4Omkpm5 --vault ~/Brains/brain

Output Format

Exported notes match Fathom skill format for consistency:

---
granola_id: not_xxxx
title: "Meeting Title"
date: YYYY-MM-DD
participants: ['Name 1', 'Name 2']
duration: HH:MM
source: granola
---

# Meeting Title

## Summary
{AI-generated summary}

## Transcript
**Speaker Name**: What they said...

Files saved as: Sessions/YYYYMMDD-meeting-title-slug.md

API Details

  • Base URL: https://public-api.granola.ai/v1
  • Auth: Bearer token (Personal API key, never expires)
  • Rate limits: 25 req burst / 5 req/sec sustained
  • Important: API only returns notes with generated summaries — in-progress meetings won't appear

Known Limitations

  • No live/in-progress access — notes appear only after Granola generates the AI summary
  • No per-utterance speaker names — Granola provides source (microphone vs speaker) and optional diarization_label. Export assigns meeting owner to microphone utterances
  • Note IDs required — use list first to get not_xxxx IDs, then show/export

Integration

  • transcript-analyzer: After export, run transcript-analyzer on the output file for deeper analysis
  • Fathom skill: Granola exports use the same frontmatter and transcript format as Fathom exports, so downstream tools work with both