name: sync-data-gcal description: > Fetch Google Calendar events via API into a JSON file. No classification, no actions — just data. Fast, no browser needed. allowed-tools: Read, Write, Edit, Bash(npx tsx .claude/skills/sync-data-gcal/*)

Sync Google Calendar Data

Calendar event ingestion via Google Calendar API. No classification, no meeting prep. Fast — no browser required. Can run as a subagent in parallel with other syncs.

Output File

outputs/sync-data/gcal.json — full replacement on every run.

Schema

{
  "version": 1,
  "last_synced": "2026-02-11T09:00:00-08:00",
  "days_fetched": 3,
  "event_count": 5,
  "events": [
    {
      "eventId": "abc123",
      "title": "Meeting with Steven (Worca)",
      "start": "2026-02-11T10:00:00-08:00",
      "end": "2026-02-11T10:30:00-08:00",
      "allDay": false,
      "location": "",
      "description": "HubSpot booking details...",
      "organizer": { "name": "Steven Lin", "email": "steven@worca.io" },
      "attendees": [
        { "name": "Simon Reisch", "email": "simon@tessel.ai", "responseStatus": "accepted" }
      ],
      "eventType": "default",
      "hangoutLink": "https://meet.google.com/...",
      "htmlLink": "https://calendar.google.com/...",
      "status": "confirmed",
      "calendarId": "primary"
    }
  ]
}

Steps

1. Run: npx tsx .claude/skills/sync-data-gcal/fetch.ts --days 3
2. Parse the JSON output. The script returns { "events": [...] }.
3. Build the output object with version, last_synced (current ISO timestamp with timezone offset), days_fetched (3), event_count, and events.
4. Write to outputs/sync-data/gcal.json (full replacement).
5. Log: "Synced {N} calendar events ({days} days) at {timestamp}"

Notes

• This skill does NOT do meeting prep. That's alfred-meeting-prep.
• The file is always the latest snapshot. No historical accumulation.
• Default is 3 days (today + 2 more). Covers Monday when run on Friday.
• Typically takes <5 seconds.