people-report

People Report

⚠️ 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 Immich's face recognition data to generate a report on people in the library: who appears most, unnamed face clusters, co-occurrence patterns, and recognition quality.

Prerequisites

• Immich's face detection and recognition must be enabled (Machine Learning container running)
• Face detection job should have completed at least once
• For best results, some people should already be named in Immich

Analysis Workflow

Step 1: Face Recognition Overview

Use the list_people MCP tool to get all people with pagination:

# Get all people (including hidden clusters)
result = list_people(page=1, size=200, with_hidden=true)
# Repeat with page=2, 3, ... until result.hasNextPage is false

# Named: people where name is not empty
named = [p for p in result.people if p.name]
# Unnamed: people where name is empty
unnamed = [p for p in result.people if not p.name]

# Top named people by face count (result includes a faceCount field)
top_named = sorted(named, key=lambda p: p.faceCount, reverse=True)[:20]

# Unnamed clusters worth naming (more than 5 faces)
big_unnamed = [p for p in unnamed if p.faceCount > 5]
big_unnamed.sort(key=lambda p: p.faceCount, reverse=True)