Media plugins

Compare two videos and generate interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Use when analyzing compression results, evaluating codec performance, or assessing video quality differences

1 skill

Download, export, save, or package images from a Google Gemini conversation page — uploaded images or generated image previews. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed files, renaming them in order, and producing a ZIP archive.

1 skill

Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.

1 skill

AI short-video production: a topic or product link becomes a finished vertical video (script → free stock footage → free TTS → captions → BGM → FFmpeg compose), keyless by default. Installs the clipforge-video skill plus the ClipForge MCP server (clipforge_create_video, clipforge_product_script, clipforge_gate …) targeting your local ClipForge instance. 一句话/商品链接直接出带货短视频。

2 skills

A browser video editor you can drive from Claude Code. The timeline is one JSON document — patch it and the open editor hot-reloads in ~150 ms. Cuts, keyframes, transitions, kinetic captions, chroma key, speed ramps, and MP4 export via ffmpeg.

3 skills · 1 MCP server

A local video studio for your coding agent. Describe a video. Your agent directs. Your machine renders. Motion graphics, voice-over, music, footage editing, captions and platform-ready exports, with no cloud AI services or API keys.

1 skill · 10 agents · 1 MCP server · hooks

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter.

1 skill

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1 skill

Professional video editing toolkit with FFmpeg operations, Whisper transcription, and Apple Final Cut Pro project generation. v1.1.0: Added explicit name: fields to commands for prefix-free invocation. Features intelligent video analysis, automated transcription with timing sync, FCPXML timeline creation.

3 skills · 3 commands · 3 agents

AI image generation and editing using Google Gemini 3 Pro Image API. v2.3.0: Added explicit name: fields to commands for prefix-free invocation (/generate instead of /nanobanana:generate). Simple Node.js CLI with markdown styles and batch generation.

2 skills · 3 commands · 2 agents

Edit your own talking-head video in a creator's measured style: retakes and pauses cut, then zooms, captions and cards rendered with Remotion on your laptop or AWS Lambda.

18 skills · 9 agents · hooks

Break down any short-form creator's videos: view counts, word-level transcripts, measured pace, cuts, zooms and caption style.

1 skill · 1 agent

Full video production studio for Remotion. AI voiceovers (ElevenLabs), music (Eleven Music), sound effects, stock footage (Pexels), AI image/video generation (KIE, Replicate), TikTok-style captions, 3D content, transitions, video analysis & review (TwelveLabs) — all wired into Remotion compositions. 13 slash commands, 3 agents, 5 MCP servers.

15 skills · 3 agents · 5 MCP servers · hooks

Produce beat-synced 1080p motion-graphic videos in HyperFrames (HTML + GSAP) with an AI voice-over, Vietnamese karaoke captions, SFX and generated music, in one of two proven styles.

1 skill

Hosted Google Flow MCP server by useapi.net (12 tools): chat with Google Flow Agent to make images and Veo 3.1 or Omni Flash (1.2 and 1.1) video, answer its credit approvals, manage chats and settings, list characters, voices and media, and upload images, on your Google AI subscription (a free account works too, Omni 1.1 Flash needs a paid one). Third-party paid service, not affiliated with Google. Includes the repo's agent skill.

1 skill · 1 MCP server

Search YouTube and download captions or audio with yt-dlp, then transcribe audio locally with Whisper (mlx-whisper on Apple Silicon, openai-whisper elsewhere)

2 skills

FFmpeg CLI reference for video and audio processing, format conversion, encoding, filtering, and media automation

1 skill

Plex Media Server management. Browse libraries, search media, manage playlists, and monitor activity.

1 skill

Prowlarr indexer management. Add, configure, test, and search indexers.

1 skill

Radarr movie management. Search, add, monitor, and manage movie collections.

1 skill

Extract relevant frames from videos and animated images (GIF/APNG/animated WebP) so LLMs can view them as a timeline. Auto-transcribes audio (whisper.cpp default) and writes a self-contained HTML report + manifest.json + ndjson run history per extract. Wraps ffmpeg with scene-change detection and fps fallback.

2 skills · hooks

Generate images, videos, and music using 600+ Fal.ai models. Supports Flux, SDXL, Kling Video, MusicGen, and more.

6 MCP servers

AI-powered visual asset management for Claude Code. Search, tag, analyze, edit, and organize your media library using natural language.

1 MCP server

Auto-dub videos into other languages with lip-sync (Perso AI Dubbing), plus voice/background audio separation and SRT subtitle extraction & translation (/srt). Single files, folders, URLs, auto split & merge for long media, multi-language output, resume.

Generate images and videos with Leonardo.Ai. Wraps the leonardo CLI and ships guides for every model family (Lucid, Phoenix, Flux, Motion 2, Veo 3, Kling, Hailuo, LTX, Seedance).

1 skill · 2 commands

One sentence in, a researched real-time 3D motion graphic out — a looping HTML film with captions, QA-checked and exported as a frame-exact MP4

1 skill

9 skills covering the full audio-to-multilingual-caption pipeline: setup, YouTube ingest, transcription, forced alignment, diarization, translation, summarization, format conversion, and viral-ready karaoke.

9 skills

Generate AI videos, images, speech, and music with varg — one API key for Seedance 2.5, Kling 4, Wan 3, Veo 3.1, Nano Banana, GPT Image, ElevenLabs and more.

81 skills · 2 MCP servers

Edit, caption, score, check and revise video with a coding agent: the film as editable text, versions that never change, plain checks and a Screening Room to watch, note and approve.

1 skill

Transcribe, translate, convert, and align captions using AI APIs

5 skills