Multimodal plugins

StarTrail-org/PixelRAG

Plugin Claude Code

Bundles 1 skill, 1 command · 102 tokens together

Give Claude eyes — screenshot any URL with pixelshot and read it visually.

tong-io/tongflow

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 87 tokens together

TongFlow media studio: plan a project as plain folders, make every image / voice / music / video / 3D asset by running a saved TongFlow workflow next to its outputs.

oxbshw/watch-skill

Plugin Claude Code

Bundles 10 skills, 1 command, 1 MCP server · 819 tokens together

Give the agent a video input via Watch Skill: watch, index, ask, and iterate (THE LOOP).

anam-org/metaxy

Plugin Claude Code

Lists 1 plugin

Plugin marketplace listing 1 plugin: metaxy.

dzivkovi/video-intel

Plugin Claude Code

Bundles 4 skills, 1 MCP server · 1,656 tokens together

YouTube video intelligence via Gemini: channel scanning, rich multimodal transcripts with on-screen content, concept taxonomy, hybrid search, and Bosnian/Croatian/Serbian subtitle translation. Three skills: video-intel (ingest/curate, runs in the plugin repo), video-intel-search (read-only, globally installable)…

kirillbrsnkv/give-claude-eyes

Plugin Claude Code

Bundles 1 skill, 2 commands · 148 tokens together

Add native video and image understanding to Claude via Qwen Omni API. Analyze videos, classify footage, extract motion data, and more.

good-boy4069/Deepseek-omnimodal

Plugin Claude Code

Bundles 1 skill, 4 MCP servers · 82 tokens together

Omnimodal plugin for Claude Code: recognize and generate images, video, and audio through Qwen, Z.AI, or OpenAI-compatible APIs.

fa-ina-tic/memvid-rag

Plugin Claude Code

Bundles 1 skill, 4 commands · 74 tokens together

Simple Local RAG based on memvid.