84 video & media Claude skills, most popular first. The most popular is hyperframes-cli. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| hyperframes-cli | 884k installs | Low risk |
| hyperframes | 846.4k installs | Low risk |
| media-use Agent Media OS for a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LU | 758.8k installs | Low risk |
| ai-video-generation | 706.9k installs | Not scanned |
| remotion-best-practices Router for all Remotion skills | 590.1k installs | Low risk |
| hyperframes-keyframes | 576k installs | Low risk |
| azure-compute Azure VM/VMSS router. WHEN: create / provision / deploy / spin-up VM, recommend VM size, compare VM pricing, V | 502.3k installs | Low risk |
| general-video | 482.6k installs | Low risk |
| video-edit | 431.7k installs | Low risk |
| hyperframes-audio | 431.1k installs | Low risk |
| image-to-video | 430k installs | Low risk |
| image-edit | 429.3k installs | Low risk |
| remotion-to-hyperframes Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to po | 405.9k installs | Low risk |
| product-launch-video Turn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, fe | 401.3k installs | Low risk |
| ai-image-generation | 390.6k installs | Not scanned |
| image-to-code | 352k installs | Not scanned |
| embedded-captions | 346.3k installs | Low risk |
| pr-to-video Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change exp | 339k installs | Low risk |
| music-to-video Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a | 321.9k installs | Low risk |
| imagegen Generate and edit images using OpenAI's Image API for projects | 28.1k ★ | Not scanned |
| sora Generate, remix, and manage short video clips via OpenAI's Sora API | 28.1k ★ | Not scanned |
| speech Generate spoken audio from text using OpenAI's API with built-in voices | 28.1k ★ | Not scanned |
| transcribe Transcribe audio files to text with optional speaker diarization | 28.1k ★ | Not scanned |
| cli Generate text, image, video, speech, and music via MiniMax AI | 13.7k ★ | Not scanned |
| gif-sticker-maker Convert photos into animated GIF stickers in Funko Pop / Pop Mart style via MiniMax API | 13.7k ★ | Low risk |
| remotion-render Export a Remotion video | 5.3k ★ | Low risk |
| remotion Programmatic video creation with React | 5.3k ★ | Not scanned |
| NanoBanana-PPT-Skills AI-powered PPT generation with document analysis and styled images | 3.3k ★ | Low risk |
| podcast-generation AI podcast audio with Azure OpenAI Realtime API | 3.1k ★ | Not scanned |
| azure-ai-vision-imageanalysis-java Image captioning, OCR, and object detection | 3.1k ★ | Not scanned |
| agents-v2-py Foundry Agents SDK — container-based agents with custom images | 3.1k ★ | Not scanned |
| azure-ai-transcription-py Speech-to-text transcription | 3.1k ★ | Not scanned |
| azure-ai-vision-imageanalysis-py Image captions, tags, OCR, objects | 3.1k ★ | Not scanned |
| azure-containerregistry-py Container image and registry management | 3.1k ★ | Not scanned |
| azure-speech-to-text-rest-py REST speech-to-text for short audio | 3.1k ★ | Not scanned |
| azure-ai-contentsafety-ts Content safety for text and images | 3.1k ★ | Not scanned |
| claude-real-video Scene-aware keyframes plus transcripts so any LLM watches videos | 2.2k ★ | Low risk |
| youtube-skills Agent skills for YouTube: pull video transcripts and discover videos (search, channel and playlist listings) v | 1.1k ★ | Not scanned |
| capcut-edit Edit CapCut and JianYing video projects from any agent | 916 ★ | Low risk |
| edit-timeline-studio Create editable video timelines with captions, voiceovers, and verified exports. | 855 ★ | Low risk |
| avatar-extraction Define exactly who the buyer is, what they want, what they've tried, and what's driving their decisions | 766 ★ | Low risk |
| claude-ai-music-skills Full-lifecycle AI music album production | 569 ★ | Not scanned |
| skills Human-like TTS workflows with local/cloud APIs and app delivery | 529 ★ | Not scanned |
| youtube-fetcher-to-markdown Create Obsidian-ready Markdown notes from YouTube videos | 492 ★ | Low risk |
| imagen Generate images using Google Gemini's API | 438 ★ | Low risk |
| video-router Route video requests through deterministic agent production stages | 331 ★ | Low risk |
| github-image-upload Attach screenshots, PDFs, logs, zips, and videos to GitHub PRs, issues, and comments, returning canonical user | 277 ★ | Low risk |
| fal-3d Generate 3D models from text or images | 252 ★ | Not scanned |
| fal-audio Text-to-speech and speech-to-text using fal.ai audio models | 252 ★ | Not scanned |
| fal-generate Generate images and videos using fal.ai AI models | 252 ★ | Not scanned |
| fal-image-edit AI-powered image editing with style transfer and object removal | 252 ★ | Not scanned |
| fal-kling-o3 Generate images and videos with Kling O3 — Kling's most powerful model family | 252 ★ | Not scanned |
| fal-lip-sync Create talking head videos and lip sync audio to video | 252 ★ | Not scanned |
| fal-realtime Real-time and streaming AI image generation | 252 ★ | Not scanned |
| fal-restore Restore and fix image quality — deblur, denoise, fix faces, restore documents | 252 ★ | Not scanned |
| fal-train Train custom AI models (LoRA) on fal.ai for personalized image generation | 252 ★ | Not scanned |
| fal-upscale Upscale and enhance image and video resolution using AI | 252 ★ | Not scanned |
| fal-video-edit Edit existing videos using AI — remix style, upscale, remove background, add audio | 252 ★ | Not scanned |
| agent Codex plugin, Agent Skill, CLI, and MCP server for publishing approved short-form videos to TikTok, Instagram | 220 ★ | Low risk |
| wonda AI content creation: images, video, music, audio, editing, publishing | 158 ★ | Not scanned |
| vibe-creating-skill Rewrites a rough idea or shot script into text-to-video prompts | 150 ★ | Not scanned |
| venice-image-generate Image generation endpoints and available styles | 148 ★ | Low risk |
| venice-image-edit Image edits, upscaling, and background removal | 148 ★ | Low risk |
| venice-audio-speech Text-to-speech models, voices, formats, and streaming | 148 ★ | Low risk |
| venice-audio-music Music generation queueing, retrieval, and completion endpoints | 148 ★ | Low risk |
| venice-audio-transcription Audio transcription models and speech-to-text options | 148 ★ | Low risk |
| venice-video Video generation and transcription workflows | 148 ★ | Low risk |
| skills Realtime and batch video workflows: capture screen/audio, ingest URLs/YouTube/RTSP, transcribe, index, search, | 133 ★ | Not scanned |
| superCMO-skills Open-source skills + local MCP server for marketing video & image production: UGC videos, ad videos, product p | 80 ★ | Not scanned |
| plugin Text or photo to game-ready GLB through Blender MCP | 48 ★ | Low risk |
| perso-dubbing-plugin Video translator: dubbing, lip-sync, subtitles, and short clips | 39 ★ | Not scanned |
| nutrient-agent-skill Document processing with Nutrient DWS API: convert (PDF/DOCX/XLSX/PPTX/HTML/images), extract text/tables, OCR | 18 ★ | Not scanned |
| agy-ppt Generate PowerPoint decks without the AI-slop look, purpose-built for the Antigravity+Kiro+Codex pipeline; GPT | 6 ★ | Low risk |
| ai-image-generation | 2 ★ | Not scanned |
| ai-music | – | Low risk |
| video-edit | – | Low risk |
| ai-image-generation | – | Low risk |
| ai-video-generation | – | Low risk |
| image-to-video | – | Low risk |
| gemini-interactions-api Building apps with the Gemini Interactions API for text, chat, streaming, and image generation | – | Not scanned |
| netlify-image-cdn Optimize and transform images via CDN | – | Not scanned |
| images-search Search for images using the Brave Search API | – | Not scanned |
| videos-search Search for videos across the web via the Brave Search API | – | Not scanned |
| cutaway Record polished demo videos of web flows with Playwright | – | Not scanned |