Granola

Skill t0ddharris/compound-marketing/.claude/skills/granola

Scale your marketing without sacrificing quality.

Install

npx -y skills add t0ddharris/compound-marketing --skill granola

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Pull meeting notes from Granola. Use when the user mentions 'Granola,' 'meeting notes,' 'pull notes from a meeting,' 'grab meeting notes,' or wants to import meeting context for content creation, brain file updates, or case study research.

SKILL.md

3.2 KB, 722 tokens by cl100k_base, as published. Nobody here has run it

Granola Meeting Notes

Pull meeting notes from Granola's API via the CLI wrapper at .claude/skills/granola/granola.sh.

Setup

The user needs a Granola API key (requires Business or Enterprise plan):

Open Granola desktop app > Settings > API > "Create new key"
Add it to the project .env file: GRANOLA_API_KEY=grn_your_key_here

If the key isn't configured, the script will tell the user what to do.

Commands

SCRIPT=".claude/skills/granola/granola.sh"

# List recent notes (last 7 days)
$SCRIPT recent

# List notes from last N days
$SCRIPT recent 30

# List with date filters
$SCRIPT list --after 2026-04-01 --before 2026-04-07

# Get a specific note (summary only)
$SCRIPT get not_ABC123DEF456GH

# Get a note with full transcript
$SCRIPT get not_ABC123DEF456GH --transcript

# Pull a note into /incoming/ (includes transcript by default)
$SCRIPT pull not_ABC123DEF456GH

# Get raw JSON output (for any command)
$SCRIPT list --json
$SCRIPT get not_ABC123DEF456GH --json

Workflow

When the user asks to pull meeting notes:

1. List available notes

Run recent or list with appropriate date filters to show what's available. Let the user pick which meeting(s) they want.

2. Fetch the note

Use get with --transcript to see the full content. Review the summary and transcript.

3. Decide where it goes

Based on the meeting content, route it appropriately:

Content type	Destination
Customer call, demo, sales conversation	`pull` to `/incoming/`, then mine for brain file updates, case study material, or audience language
Product feedback, feature requests	Extract insights, suggest updates to `/brain/truth.md` or `/brain/positioning-and-messaging.md`
Internal strategy discussion	Summarize key decisions, suggest project memory updates
Partner or analyst meeting	Extract relevant intelligence for `/brain/market-signals.md`
Content planning meeting	Extract ideas for `/marketing/inspiration/content-ideas.md`

4. Process the notes

Apply the same rigor used for Apollo transcript mining:

Interpret through context (meeting notes may have transcription errors)
Extract actual customer/prospect language for /brain/audience-language.md
Identify conversion triggers and objections for /brain/customer-journey.md
Flag any product claims that need verification against /brain/truth.md
Never parrot raw transcript, always synthesize

Important Notes

The API is read-only and returns only notes with AI-generated summaries
No search endpoint exists; use date filters to narrow results, then review locally
Page size max is 30; use --cursor for pagination
Rate limit: 5 requests/second (burst 25). Don't hammer it
Transcript speakers are labeled "You" (microphone) and "Other" (speaker audio); actual names come from the attendees list
The /incoming/ folder is the user's drop zone; pull writes there by convention so the standard intake workflow applies

Gives 0 of the 12 instructions most note taking skills give in 722 tokens

Counted across 686 of the 876 authors here whose files we hold, read 2026-08-06

include a visual element on every slidein 44 of 686, across 13 files
use wikilinks for internal vault linksin 35 of 686, across 11 files
commit to a single visual motif across every slidein 34 of 686, across 9 files
read pptxgenjs guide before creating presentations from scratchin 30 of 686, across 6 files
keep 0.5 inch minimum marginsin 30 of 686, across 7 files
use subagents to visually inspect rendered slidesin 30 of 686, across 6 files
re-verify affected slides after every fixin 27 of 686, across 5 files
run content QA checks before declaring successin 26 of 686, across 3 files
Use Markdown links for external URLs onlyin 26 of 686, across 10 files
pick a bold topic specific color palettein 24 of 686, across 2 files
read editing guide before editing existing presentationsin 23 of 686, across 1 file
use one dominant color across all slidesin 23 of 686, across 1 file

Said here and by no other author read

Pull meeting notes via the Granola CLI wrapper
List available notes using date filters
Let the user pick which meetings they want
Fetch the note with the transcript flag
Route meeting content based on its type
Extract customer language into the audience file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.