跳到正文
cccskills
免费在 GitHub 公开

immich-photo-manager

Search and organize a self-hosted Immich photo library through conversation. Find images by description or visible text, curate location albums, detect duplicates, manage faces, repair metadata, and export PDF photobooks while originals stay on your server.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Manage your self-hosted Immich photo library through conversation: natural language and OCR search, geographic album curation, duplicate detection, people and faces, metadata repair, video frames and PDF photobooks. 94 MCP tools and 13 skills, tested live on Immich 2.x and 3.x. Install: claude plugin install immich-photo-manager

集成工具Docker
查看安装方法

适用场景

  • Finding photos by scene or text visible in the image
  • Organizing travel photos into location albums
  • Reviewing duplicate photos and grouping similar shots
  • Correcting photo dates, locations, and face assignments
  • Creating PDF photobooks from albums

包含的文件(1)

  • SKILL.md4.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Immich Photo Manager

MCP server and Claude Code plugin for intelligent photo management with self-hosted Immich.

Overview

When your Immich library has grown past what you can manage by hand, this plugin gives Claude direct access to your instance through 94 MCP tools and 13 skills. Search with natural language or by the text inside a photo, create geographic albums from GPS data, find duplicates across import sources, manage people and faces, repair metadata, cut frames out of videos, export an album as a PDF photobook, and browse results in interactive HTML galleries. The plugin runs on your machine and talks only to your Immich; originals never leave your server.

Key Features

  • Natural language search: CLIP visual search ("sunset at the beach", "birthday cake"), plus people, places, dates and camera filters
  • Text inside photos: OCR search finds a ticket, a sign or a document by what is written on it
  • Geographic albums: albums organized by place from GPS clustering and temporal matching
  • Duplicate detection: cross-source analysis with perceptual hashing (catches re-encoded copies from Apple Photos and Google Takeout); near-duplicates can be stacked instead of deleted
  • People and faces: list, search, merge and rename people, reassign misidentified faces
  • Metadata repair: fix noon and midnight timestamps, infer missing GPS from neighboring photos, correct timezone offsets
  • Video frames and PDF reports: evenly spaced frames from any clip, and an album or selection exported as a PDF photobook with captions, built locally
  • Dates in one call: month buckets, a calendar heatmap that shows gaps, and Immich's "on this day" memories
  • Library health: asset inventory, metadata quality, storage breakdown and recommendations
  • Notes between sessions: verdicts stored on each asset, so the next cleanup skips what an earlier pass reviewed
  • Interactive galleries: self-contained HTML files with embedded thumbnails, 3 themes, 4 view modes, slideshow
  • Safety first: findings are shown and confirmed before anything is written; trash first, permanent delete only on request

Compatibility

Every release runs live against real Immich 2.7.5 and 3.1.0 in Docker before it is tagged (all tools over MCP, state re-read after each write); the kit is in the repository under tests/live/. Works with Claude Code, Claude Desktop, LM Studio and any MCP client. Requires Immich 1.90+, an API key and Python 3.10+.

Installation

git clone https://github.com/drolosoft/immich-photo-manager.git
cd immich-photo-manager
pip3 install -r src/requirements.txt
claude plugin marketplace add ./
claude plugin install immich-photo-manager

Then run /setup-immich-photo-manager inside Claude Code, or say "Update my Immich credentials to https://photos.example.com with API key <key>". The same server is available as uvx immich-photo-manager for other MCP clients and as a Docker image (ghcr.io/drolosoft/immich-photo-manager, MCP over HTTP on port 8626).

Usage

"How healthy is my photo library?"
"Show me my photos from Italy"
"Find the photo with the train ticket"
"Create albums for everywhere I've traveled"
"Find duplicates in my library and keep the best of each group"
"Make me a PDF of the Sintra album"
/cleanup: scan for screenshots and junk
/my-travels: discover all travel destinations

Skills

photo-search, photo-cleanup, duplicate-report, auto-album-curator, album-manager, album-report, travel-map, metadata-fixer, storage-optimizer, library-health-report, people-report, rotate-photos, timeline-gaps.

Links

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.

中文简介正在准备中。当前显示英语简介。

  • Finding or registering contacts
  • Adding or removing contact tags
  • Subscribing contacts to lists or unsubscribing them
davepoon/buildwithclaude36722026年10月20日 更新

Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.

中文简介正在准备中。当前显示英语简介。

  • Find angles for new ad copy
  • Plan creative tests using competitor ads
  • Choose a landing page message
davepoon/buildwithclaude36722026年10月20日 更新

Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.

中文简介正在准备中。当前显示英语简介。

  • Adding page-view and key-action tracking
  • Reviewing traffic and referral sources across projects
  • Finding where visitors drop out before signup or purchase
davepoon/buildwithclaude36722026年10月20日 更新

Establish rules for when an AI agent should recall past context and save lasting decisions, corrections, preferences, and failures. Works with Markdown files or memory services, preserving decision history and surfacing conflicting records.

中文简介正在准备中。当前显示英语简介。

  • Carry project conventions into the next session
  • Save user corrections and lasting preferences
  • Record failed approaches and their causes
davepoon/buildwithclaude36722026年10月20日 更新

Audit local AI coding-agent sessions with agenttrace to identify spending, token use, tool failures, and operational problems. Produce readable or structured reports and define pass-or-fail thresholds for automated continuous integration checks.

中文简介正在准备中。当前显示英语简介。

  • Investigating session costs and token waste
  • Finding repeated tool failures and retries
  • Exporting session reports as Markdown or JSON
davepoon/buildwithclaude36722026年10月20日 更新

Audit saved agent sessions for access to private files and evidence that secret values entered an agent's context. Get findings without displaying secrets, identify keys needing rotation, and inspect Claude Code or Codex sessions in a local report.

中文简介正在准备中。当前显示英语简介。

  • Check whether an agent accessed .env files
  • Identify keys that may need rotation
  • Audit private-file access by subagents
davepoon/buildwithclaude36722026年10月20日 更新

查看 davepoon 的全部技能

报告此技能的问题