querying-granola

Queries local Granola meeting cache for meeting history, context, and attendee information. Use when preparing for meetings, researching past interactions with a person or company, finding past discussions on a topic, tracking engagement, or when user mentions Granola, meeting notes, meeting history, or attendees.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "querying-granola" with this command: npx skills add asterlabs-ai/querying-granola/asterlabs-ai-querying-granola-querying-granola

Querying Granola

Query the local Granola meeting cache. Requires Python 3.

Note: This reads from an unofficial local cache file, not a Granola API. The cache format could change with Granola updates.

Run this script to query meetings:

python3 skills/querying-granola/scripts/granola.py <command> [args]

Do not read the script source; execute it with the commands below.

Primary Commands (search by title/notes/attendee names)

CommandPurpose
client <name>Get meetings matching name in title, notes, or attendee names/emails
search <query>Search by keyword in title, notes, or attendees
context <title>Get full notes + transcript for a specific meeting

Domain-Based Commands (require @domain.com in attendee list)

CommandPurpose
profile <domain>Company/org profile with contacts and meeting history
active [N]Most active domains in last N days (default 30)
stale [N]Domains with no meetings in N+ days (default 60)
domainsMeeting counts by email domain

Other Commands

CommandPurpose
timeline <query>Meeting frequency over time (visual bar chart)
recent [N]List N most recent meetings (default 20)
peopleMeeting counts by person

Workflows

Before a meeting

Progress:
- [ ] Run profile for company/person context
- [ ] Run search for recent meeting history
- [ ] Identify key topics and contacts
- [ ] Check for unresolved action items
  1. profile domain.com → contacts, meeting count, recent notes
  2. search "PersonName" or client "CompanyName" → recent meeting notes
  3. Review for action items, open questions

Engagement tracking

Progress:
- [ ] Check active domains for recent engagement
- [ ] Check stale domains for follow-up opportunities
- [ ] Review timeline for engagement patterns
  1. active 30 → who you've been meeting with recently
  2. stale 60 → contacts you haven't met with in a while
  3. timeline "name" → meeting frequency over time

Output Examples

profile returns: meeting count, date range, contacts with meeting counts, recent meeting previews.

timeline returns: monthly bar chart showing meeting frequency with sample titles.

active/stale returns: domain, meeting count, top contacts.

Data Sources

The script extracts from multiple cache sections:

SourceContains
documentsMeeting title, date, user-typed notes, basic attendees
documentPanelsAI-generated summaries (comprehensive meeting notes)
meetingsMetadataEnriched attendee info with company names
transcriptsRaw meeting transcripts (~8 recent meetings cached locally)

Notes priority: AI summaries are preferred over user-typed notes when available (more comprehensive).

Company names: Displayed as Name <email> @ Company when enriched data exists.

Transcripts: Only available for recent meetings; displayed in context command when present.

Limitations

Domain-based commands (active, stale, profile) only work when attendee emails are captured in the meeting invite. If you join someone else's meeting link (their Zoom/Meet), their email may not be in your attendee list. Use search or client by name/title for these cases.

Transcripts are only cached locally for recent meetings (~8). Older meetings won't have transcript data available.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Research

learn-anything-in-one-hour

Teach users any new skill/knowledge X in ~1 hour using a fixed 4-step workflow optimized for complete beginners, focusing on 80/20 rule for maximum value in minimum time. Triggers when user asks to learn something new quickly, or mentions "learn X in one hour".

Archived SourceRecently Updated
Research

X/Twitter Research

# X/Twitter Research Skill

Archived SourceRecently Updated
Research

council

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.

Archived SourceRecently Updated
Research

polymarket-openclaw-trader

Reusable Polymarket + OpenClaw trading operations skill for any workspace. Use when the user needs to set up, run, tune, monitor, and deploy an automated Polymarket trading project (paper/live), including env configuration, risk controls, reporting, and dashboard operations.

Archived SourceRecently Updated