timeline-gaps

Timeline Gaps

⚠️ Connection Required: ALWAYS CHECK FIRST

Before doing ANYTHING else in this skill, call ping on the Immich MCP server.

• If ping succeeds → proceed with the skill normally.
• If ping fails or the MCP tools are not available → STOP. Do not continue. Tell the user:

❌ Immich is not connected. This plugin needs a running Immich MCP server to work.

Run /setup-immich-photo-manager to configure your Immich connection. You'll need:

1. Your Immich server URL (e.g., http://192.168.1.100:2283)
2. An Immich API key (how to create one)
3. The MCP server configured (see /setup-immich-photo-manager)

Nothing in this plugin will work until the connection is configured.

Do NOT skip this check. Do NOT try to run any other tool first. Always ping, always block if it fails.

Analyze the photo timeline month by month to detect gaps, anomalies, and coverage issues across import sources. Helps users discover missing imports, backup failures, or periods where photos only exist in one ecosystem.

When to Use

• After importing from multiple sources to verify nothing was missed
• Periodic checkup to ensure continuous coverage
• Before deleting an import source to verify the other source covers those periods
• Investigating why certain memories seem to be missing

Analysis Workflow

Step 1: Build Monthly Timeline

Generate a complete month-by-month matrix across all sources. The MCP tool get_timeline_buckets returns one bucket per month with its asset count in a single call, so start there, and use the SQL below only when the per-source split matters, since the buckets do not know where a photo was imported from. The plugin never provides database access: the query is for a user who already has psql on their own Immich.

WITH months AS (
  SELECT generate_series(
    date_trunc('month', min("localDateTime")),
    date_trunc('month', max("localDateTime")),
    '1 month'::interval
  ) as month
  FROM asset WHERE "deletedAt" IS NULL
),
source_counts AS (
  SELECT
    date_trunc('month', "localDateTime") as month,
    CASE
      WHEN "originalPath" LIKE '%Apple%' THEN 'Apple'
      WHEN "originalPath" LIKE '%Google%' THEN 'Google'
      ELSE 'Other'
    END as source,
    count(*) as cnt
  FROM asset WHERE "deletedAt" IS NULL
  GROUP BY 1, 2
)
SELECT
  m.month,
  coalesce(sum(cnt) FILTER (WHERE source = 'Apple'), 0) as apple,
  coalesce(sum(cnt) FILTER (WHERE source = 'Google'), 0) as google,
  coalesce(sum(cnt) FILTER (WHERE source = 'Other'), 0) as other,
  coalesce(sum(cnt), 0) as total
FROM months m
LEFT JOIN source_counts sc ON m.month = sc.month
GROUP BY m.month
ORDER BY m.month;