Media plugins

Generate and edit images through the Codex CLI on your ChatGPT plan (no API key), with what each image cost in your Codex limits

1 skill

Edit video with Zornov: Claude makes, cuts, checks and exports Zornov projects with Zornov's own tools

1 MCP server

Skills and MCP engine for short-form edits, generated films and character swaps.

4 skills · 1 MCP server

BETA. Turn a recorded webinar into a publish-ready YouTube video — pull the recording off the platform, cut filler words and the dead cold open using word-level transcript timing plus audio-energy boundaries, build a thumbnail that survives at 168px, generate chapters by OCR-ing the slides, and upload private for review. Verifies itself by re-transcribing the render.

1 skill

通过 ffmpeg/ffprobe 处理音视频文件：压缩、转码、裁剪、缩放、变帧率、抽取音频、混流、拼接、字幕烧录、加水印与媒体检查

1 skill

动效与视觉特效工程顾问：把目标效果或参考视频拆解到 20 项工具的具体能力与功能入口，覆盖网页动画、Three.js/Blender、粒子/物理/后期、代码视频、生成素材、声音同步、录制导出，并诊断渲染、性能、时序与交付问题

1 skill

Agent Skill and MCP server that compile audio timelines into mastered audio and subtitles.

1 skill · 1 MCP server

Local text-to-speech — 30 languages, voice design, voice cloning. Free, offline, Apple Silicon.

1 skill

8-tool local AI music production — generate, separate stems, convert voice

音视频处理：分析、转码压缩、裁剪缩放、音轨提取与音频转换、视频截图、在线下载与播放预览

11 skills

音视频处理：分析、转码压缩、裁剪缩放、音轨提取与音频转换、视频截图、在线下载与播放预览

11 skills

Generate images, videos, podcasts, presentations, and data charts from text descriptions.

9 skills

把 QQ 音乐 Mac 的加密下载（.mgg/.mflac）批量转成 Shokz OpenSwim Pro 可播放的 MP3/FLAC，自动跳过已转换文件，可选清理源文件并引导拷贝到耳机。

5 skills

Run Nano Banana image generation, Veo video generation, and FFmpeg stitching through MCP.

2 skills · 1 MCP server

VidLens: video metadata, frames, scene cuts, contact sheets, clips (ffmpeg + Bun)

1 skill · 1 command

Generate video, images and voice-over with apimodels.app (Seedance, Veo, Kling, MiniMax Hailuo, Wan, GPT Image, Nano Banana, Seedream, ElevenLabs, ...).

1 skill · 1 MCP server

AI media generation skill: Seedance 2.5, GPT Image 2.5 Sunburst, Nano Banana 2 / Pro, Flux 3, Gemini Omni Video, Kling, Topaz upscale, video ad replication, product-URL video ads. Multi-segment UGC pipeline with voice continuity. Includes per-model reference cards, model-agnostic concept docs, and the canonical talking-avatar workflow.

1 skill

Turn a raw screen recording or talking-head video into a finished edit: pauses cut, word-by-word captions, zooms, spotlights, motion-design cards and website screenshots as B-roll, in one of 20 animation styles or styled after your own website. You approve every still on a local review page before the MP4 is rendered. No Hyperframes, no Remotion.

1 skill

Generate polished demo MP4s from Playwright specs with captions, ElevenLabs voiceover and background music. Requires ffmpeg, Node 18+ and Playwright in the target project.

1 skill

Build a YouTube-ready MP4 from narrated audio plus a slide deck, cutting slide changes to the transcript. Requires ffmpeg, uv, poppler and LibreOffice for PPTX input.

1 skill

Image editing, batch operations, format conversion (WebP, AVIF, JPEG XL, PDF), metadata, and library organization — bucket by resolution, aspect ratio, orientation, format, capture time, and camera; dedupe near-duplicates.

28 skills · 19 commands

AI media production — Higgsfield model selection and production workflows, Magnific spaces/flows/designer, HeyGen avatar video, Mux streaming, and video content strategy.

44 skills

agentY MCP server + agentY skills + role subagents + /agenty commands. Needs uv and git on PATH; the first start builds its Python environment (slow once).

30 skills · 5 commands · 2 agents · 1 MCP server

Drive an AI-generated video project end to end — brief, model selection, characters, script, storyboard, generation pipelines (text-to-image, image-to-video, voice, lip-sync), GPU-aware assembly, ComfyUI import/export, budgets, export — plus a curated index of agent-callable video and audio tooling.

13 skills · 11 commands · 7 agents · 3 MCP servers

Edit video by talking to Claude Code, in your style and with your sign-off: import footage, find the best moments, cut, caption, fix the sound, add graphics, check the finished file and deliver it. Needs the metarush program installed (metarush setup).

16 skills · 1 MCP server

The full AudioPod toolkit, including music, text to speech, and voice tools, plus transcription, stem separation, noise removal, speaker separation, and format conversion.

9 skills · 5 commands · 1 MCP server

Agent Skills for Seedance 2.5 / Mini / Fast, Wan, Kling, Seedream and MiniMax via PowerTokens — product ads, UGC, pipeline, product bible QC. One API key; Claude Code / Codex / Cursor.

13 skills

Official ElevenLabs skills, tracked from a light fork of elevenlabs/skills: text-to-speech, music, sound effects, dubbing, speech-to-text, voice changer, voice isolator, speech engine, and conversational agents. Needs ELEVENLABS_API_KEY.

11 skills

Plan and execute video edits like a professional editor. Ships an editorial-craft skill, a researched platform safe-zone reference with a verification overlay, a portable Edit Plan format, and an OpenCut MCP adapter.

6 skills · 5 commands

AudioPod's audio-processing tools: speech-to-text, stem separation, noise removal, speaker separation, and format conversion.

6 skills · 4 commands · 1 MCP server