Media plugins

Generate images with the Codex CLI's built-in $imagegen skill, save them into the project, and remove each run's generated_images cache folder so storage stays flat.

1 skill

Hosted Muse MCP server by useapi.net (37 tools): make Muse images and videos, chat with the Muse agent and answer its permission requests, use the agent's browser and manage the Library, on your Muse (muse.ai) subscription, the free plan included. Third-party paid service, not affiliated with Meta. Includes the repo's agent skill.

1 skill · 1 MCP server

Make and review swift-render videos (SwiftUI scenes rendered to MP4) from any Swift codebase: the swift-render MCP server (21 tools: launch films, scenes, props, frames, renders as jobs, the API guide, the review loop), the swift-render-make and swift-render-review skills and the swift-render-director agent.

2 skills · 1 agent · 1 MCP server

ElevenLabs AI 음성 생성, 사운드 이펙트, 음성 클론 등 오디오 제작 도구

3 skills · 3 commands

Archive YouTube videos with yt-dlp: download 480p video, transcript, description, metadata, thumbnail, and chapters. Chains fabric skills for analysis.

1 skill

Comprehensive image processing for Genkit - generation, editing, analysis, optimization with Claude Vision, DALL-E, Stable Diffusion, and Sharp

Comprehensive audio processing for Genkit - generation, transcription, translation, speech synthesis with OpenAI Whisper, ElevenLabs, Google TTS, and FFmpeg

Comprehensive video processing for Genkit - generation, editing, analysis, transcription with FFmpeg, Runway ML, and AI video tools

Generate blog cover images, architecture diagrams, and process infographics as PNG using HTML+CSS rendered via Chrome headless.

3 skills

Generate multi-frame Excalidraw diagrams from a design doc with a tested builder: layout checks, SVG/PNG preview, structure validation, and a facts cross-check against the source.

1 skill

Make videos from code: Remotion or fframes for motion, p5.js for canvas, Cairo/Skia/Poppler for 2D, Python + Vulkan (wgpu) for shader frames, Python for MIDI and synth audio, ffmpeg to stitch. Renders once and never judges its own output.

1 skill

Generate images, videos, audio, and more using fal.ai AI models from Claude Code.

1 skill · 1 MCP server

Free CC0 sound effects for apps and games: the SFXMint MCP server and skill.

1 skill · 1 MCP server

Edit vertical short videos (Reels, Shorts, TikTok) from talking-head footage in Claude Code, or cut a long podcast, webinar or interview into a series of clips: cut pauses and retakes by audio, virtual camera and on-brand motion graphics in Remotion, designed scenes for hooks, quotes, numbers and calls to action, word-timed subtitles, face-aware layout, loudness mastering and a 1080×1920 render. Brand profiles with a brand tone. Runs locally with ffmpeg, Node.js and Python.

1 skill

Optional add-on for IT Reelsmaker: vertical stock footage (Pixabay, Pexels, Magnific), CC-licensed memes (Openverse) and paid AI video generation (Veo, Kling, LTX via fal.ai) for B-roll, a more accurate transcript (OpenAI text on the local word times), subtitle translation (Claude, OpenAI, Gemini), plus figure cut-outs on your own server over SSH. Every download and paid run only after you approve the visual plan.

1 skill

Create, preview, check and render videos from Claude Code. Adds the genmotion MCP tools and a make-video skill.

35 skills · 1 MCP server

Lipsync videos, make photos and AI characters talk, translate and dub videos, fix spoken words, localize campaigns, run batch lipsync, and build sync. into apps. Uses the hosted sync. MCP server.

10 skills · 1 MCP server

Review, tag, cut, and reframe video locally. Pluggable providers for transcription, tagging, and visual perception — no vendor lock-in, no auto-publish.

4 skills · 1 command · 1 MCP server

Make, check, render and deliver films in code with Shaderera, and search and add Shaderera's own plugins (building blocks for films).

2 skills · 1 MCP server

Automated vertical clip creator for talks: whisper + Claude (moments + smart crop) + ffmpeg, with safer script argument handling and error reporting

6 skills · 3 commands · 3 agents

Bridge between a short brief and image-gen web UIs (Gemini/ChatGPT/Grok/Midjourney). Crafts target-tuned prompt, copies to clipboard, opens the UI — no API keys; frontmatter parsing no longer reopens from markdown hr lines.

5 skills · 4 commands

Extract the most meaningful, engaging clips from YouTube videos. Analyzes transcripts to find high-value segments based on controversy, insightful analysis, or user-specified topics.

1 skill

Add burned-in subtitles to a video the user uploads or points to on disk. Transcribes the audio with Whisper and burns styled captions directly into the video.

1 skill

Extract the most controversial or genuinely-novel insights from a YouTube video and output them both as a .txt file and printed in the terminal. Optionally web-checks ideas for novelty.

1 skill

Media Engineering: music, audio, video, TV, film and podcast engineering for software engineers — the fundamentals of digital media, containers and codecs as engineering choices, audio production and plugin formats, video production, colour and timecode, loudness standards and why your mix is quiet on streaming, transcoding pipelines and ABR packaging, streaming delivery (HLS, DASH, CMAF, WebRTC and Media over QUIC), DRM, captions and accessibility, podcast infrastructure and dynamic ad insertion, metadata and rights identifiers, and the AI generation layer with its live licensing fight.

5 skills

Generate, edit, remix, and optimize images with Google Gemini image models.

1 skill · 5 commands · 5 agents

Speak text through multiple providers with owned playback cleanup and cost estimates.

1 skill · 7 commands · hooks

Generate, edit, and batch-create images via OpenAI Codex CLI (gpt-image), billed against the user's ChatGPT subscription. No API key, no per-image $ charges.

1 skill · 4 commands · 1 MCP server

Generate and edit Excalidraw diagrams from natural-language prompts and code context.

1 skill · 1 command · 1 agent

Hosted Google Vids MCP server by useapi.net (18 tools): make Gemini Omni 1.2 Flash video of up to 15 seconds, images, AI avatars from a photo or a description, 30-second talking avatar videos and speech in Google Vids, extend, edit and upscale clips, on your Google AI Plus, Pro or Ultra subscription. Third-party paid service, not affiliated with Google. Includes the repo's agent skill.

1 skill · 1 MCP server