name: sync-data-gmail description: > Fetch email threads from Gmail 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-gmail/*)

Sync Gmail Data

Email ingestion via Gmail API. No classification, no triage, no Gmail actions. Fast — no browser required. Can run as a subagent in parallel with browser-based syncs.

Output File

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

Schema

{
  "version": 1,
  "last_synced": "2026-02-11T09:00:00-08:00",
  "account": "steven@worca.io",
  "thread_count": 100,
  "threads": [
    {
      "threadId": "19c4d20aa13f8ca0",
      "messageId": "19c4d20aa13f8ca0",
      "from": "justinchi.g@example.com",
      "fromName": "Justin Chi",
      "to": "tiwen@worca.io",
      "subject": "outbound for Worca",
      "date": "2026-02-11",
      "body": "First 1000 chars of latest message...",
      "labels": ["UNREAD", "IMPORTANT", "INBOX"],
      "messageCount": 1,
      "participants": [{"name": "Justin Chi", "email": "justinchi.g@example.com"}]
    }
  ]
}

Steps

1. Run: npx tsx .claude/skills/sync-data-gmail/fetch.ts --count 100
2. Parse the JSON output. The script returns { "threads": [...], "count": N }.
3. Build the output object with version, last_synced (current ISO timestamp with timezone offset), account ("steven@worca.io"), thread_count, and threads.
4. Write to outputs/sync-data/gmail.json (full replacement).
5. Log: "Synced {N} email threads at {timestamp}"

Notes

• This skill does NOT classify, triage, or take Gmail actions. That's alfred-email-triage.
• The file is always the latest snapshot. No historical accumulation.
• Typically takes <10 seconds.