Video & audio
3,623 rows, by stacks then stars
782 of these skill files have been read, by 619 distinct authors, and what they tell an agent counted. What Video & audio authors agree on, and what they forbid
SkillMedev/motion-video-direction/skills/kinetic-typography Skill
0★ repoThe craft layer for software video — storyboarding, motion principles, type, color, sound, and social cutdowns
kugamon/youtube-transcript-plugin/plugins/youtube-transcript/skills/youtube-transcript Skill
0★ repoClaude Desktop / Cowork plugin to extract transcripts from YouTube videos, with or without timestamps.
SkillMedev/remotion-video-production/skills/remotion-compose Skill
0★ repoTurn natural language briefs into rendered MP4s using Claude Code and Remotion — covers project setup, composi
SalZaki/ffmpeg-workbench/skills/ffmpeg Skill
0★ repoA Claude Code plugin for ffmpeg which encode, compress, resize, trim, concat, GIFs, audio, subtitles, and platform packaging. Reference-driven recipes with an eval harness
johnisanerd/claude-skill-youtube-transcript-api/apify-youtube-transcript-api Skill
no license0★ repoClaude/agent skill: get YouTube transcripts as JSON, SRT, or VTT via a hosted YouTube transcript API (Apify)
Apify youtube transcripts llm training data
johnisanerd/claude-skill-youtube-transcripts-llm-training-data/apify-youtube-transcripts-llm-training-data Skill
no license0★ repoClaude/agent skill: build LLM training data from YouTube transcripts in bulk (Apify)
fantasybz/trip-pwa-skills/skills/food-ingest Skill
0★ repoClaude Code skill bundle that compiles a curated, offline-first family-travel PWA — you own the artifact (HTML/CSS/JS/JSON), deploy to GitHub Pages, works on the plane
Script to video production agent
jackterror/script-to-video-production-agent Skill
0★A modular AI-ready script-to-video production agent that turns tutorial scripts into narration-locked scenes, reviewable visual direction, prompt packs, and local asset queues.
web594/resolve-multicam-workflow Skill
0★Claude Agent skill for DaVinci Resolve Studio: audio sync, auto multicam cut from a Whisper transcript, film-look grading via shared Color-Group nodes, non-destructive blur/shake QC with angle switching, overlay titles. By wunder-media.
huangjie127/pitch-video-auto-generation Skill
0★A Claude Code / Claude Agent skill that turns a product website URL into a finished ~30s MP4 pitch video in Apple-launch style — AI-generated cinematic shots, AI soundtrack, pixel-perfect typography overlaid in post, auto-stitched with ffmpeg.
doramirdor/ppt90s/skills/ppt90s-video Skill
0★ repoTurn photos into a 90s PowerPoint-style video: WordArt, clip art, cheesy animations, and a Solitaire card-cascade finale. CLI + Claude Code skill.
jk241282/-deepseek-skills/audio-local Skill
no license0★ repo给 Claude Code + DeepSeek 装上眼睛和耳朵：本地多模态 Skills 套装，支持图片识别/OCR（Ollama minicpm-v）和语音转文字（faster-whisper large-v3-turbo），纯本地运行无需云服务
Poe api universal generator skills
wedsamuel1230/poe-api-universal-generator-skills Skill
0★Agent skills package for universal Poe API requests using POE_API_KEY, supporting LLM chat plus image, video, and audio generation with mode-based routing, retries, and reproducible outputs.
yaniv-golan/transcription-reader-skill/skills/transcription-reader Skill
0★ repoAI agent skill for reading SRT, VTT, STJ, and ASS subtitle files — strips timing metadata for 40–90% token savings. Works with Claude, ChatGPT, Cursor, Codex & more.
1-SKILL/ai-shu Skill
no license0★长内容转电子书 — 丢一个链接进来,拿一本书出去
liaozicen666-tech/AI-podcast-dual-host-mandarin Skill
0★中文人格化对谈音频播客skill
ThePlasmak/super-transcribe Skill
0★An OpenClaw skill that uses faster-whisper and Parakeet to transcribe audio quickly, with additional features such as speaker diarization
lunaticfluker/fal-ai-skill Skill
0★Claude Code skill for fal.ai — image, video & audio generation with Flux Pro, Kling, and 600+ models
yaniv-golan/ytd-skill/skills/youtube-downloader Skill
0★ repoAI agent skill for downloading YouTube videos with interactive resolution and subtitle selection
Freephagocyterusher317/pollo-skills/skills/pollo-ai-video-generator Skill
0★ repoEnable AI agents to generate videos, process media, and manage tasks using Pollo AI's official skills and models.
marmot-sh/marmot/skills/marmot Skill
0★ repoOne CLI for your agent and scripts for AI, search, scraping, and enrichment.
Genpark nano banana video orchestrator
Alpha-Park/genpark-nano-banana-video-orchestrator Skill
no license0★GenPark Distilled Skill: nano-banana-video-orchestrator
ploteddie-bit/skills/ASR Skill
no license0★ repoCollection de compétences agentiques modulables pour Kimi, Aegis et assistants IA
Terminusapp-ai/watch-video/plugins/watch-video/skills/watch-video Skill
0★ repoA Claude Code skill that lets Claude watch a video by extracting frames with ffmpeg and reading them through its native image tool.
arpitexplores/super-gaming-3d-media Skill
0★Portable Markdown skill for AI vibe coding with games, 3D, and media: Unity, Unreal, Godot, Three.js, animation, audio/video workflows, assets, and performance.
tRollNhard/1st/.claude/skills/remotion-best-practices Skill
no license0★ repo0SxD/youtube-transcript-skill Skill
0★ciro-rosa/claude-skills/transcribe-and-cut-video Skill
no license0★ repoClaude agent skills — transcribe-and-cut-video and more
6uclz1/skills/.agents/skills/youtube-gemini-proxy Skill
0★ reposyncfusion/vue-ui-components-skills/skills/syncfusion-vue-ai-assistview Skill
no license0★ repoThis repository contains agent prompts for creating skills and organizing AI agent capabilities.
vox4ai/vox4ai-agent-skills/skills/vox4ai-tts Skill
0★ repoVasileiosMalt/investigation-skill-poirot Skill
no license0★Agent skill for case investigation that finds evidence and patterns across photos, audio, video, and text from a specific case-related directory.
g0dam/video-studio-skills/video-asset-bible Skill
0★ repoModular agent skills for AI video production, from taste profiling to release QA.
DentVega/firebase-agent-skills/skills/firebase-ai-logic Skill
0★ repoCommunity Firebase agent skills for AI coding assistants — Expo / React Native focus
YYH123123813/video-prompt-lab/skills/video-prompt-lab Skill
0★ repoLocal-first AI-video prompt generator, linter, and eval kit. One ShotSpec YAML -> Sora/Veo/Runway/Kling/Seedance prompts.
frankxai/awesome-motion-design-agent-skills/skills/generative-media-director Skill
no license0★ repoTHE definitive curated resource for motion-design-agent-skills | GenCreator 6-Pillar CoE • Starlight Intelligence • Arcanea Creative Execution • Agentic Passive Income Systems
breakthrough-edu/youtube-transcript-ingestion Skill
0★A Claude Code skill that turns any YouTube channel into clean, searchable transcript files -- with built-in rate-limit handling.
creative-int/keris-plugins/skills/keris-video-proof Skill
0★ repormichak/code-walkthrough-video-builder/skills/code-demo-video Skill
no license0★ repoBuild coding & lecture videos programmatically — simulated VS Code typing, TTS voiceover, captions, and overlays. No screen recording required. Two HyperFrames Agent Skills.
billwang233/douyin-web-control-skill/skills/douyin-web-control Skill
0★ repoAgent skill for controlling Douyin web through the douyin-web CLI
Amazing-soil/santu61ai-skill/ai-tech-video-production Skill
0★ repo三土沉淀的 AI Agent Skills 合集，包含中文 AI 科技口播视频生产等可复用工作流。
breakthrough-edu/meeting-scribe/meeting-scribe Skill
no license0★ repoLocal, cross-platform meeting transcription -> corrected transcript + Precision Pro HTML canvas + AI-insight summary. A Claude Code skill.
lynseylee-ones/transcript-clean-translate-en Skill
no license0★Agent skill for cleaning Chinese ASR transcripts and translating them into natural English for Codex and Claude Code.
Nu424/agentic-video-analysis-skill/skills/agentic-video-analysis-skill Skill
no license0★ repoエージェンティックに動画解析するためのAgent Skills + スクリプト
ModelTC/LightX2V-Skills/.agents/skills/lightx2v-ai-video-generation Skill
0★ repoAgent skills for LightX2V — teach Cursor and AI agents to generate images & videos (t2v, i2v, t2i, s2v) via the lightx2v CLI and x2v.light-ai.top OpenAPI.
satishTheLegend/single-source-content-factory Skill
0★Maintains ONE canonical asset as the source of truth and derives every channel atom — blog, newsletter, LinkedIn, X thread, short-video script, email — from it, with traceability and brand-voice gates so nothing drifts.
jessepwj/video-use-hyperframes-editor-skill/skill/video-use-hyperframes-editor Skill
0★ repoAgent Skill for careful talking-head video cleanup, HyperFrames motion planning, preview confirmation, and final MP4 export.
mindcruiser/notta-mcp-skill Skill
no license0★ryanwi/agentic-remotion-pipeline Skill
0★Agent-drivable Remotion pipeline: structured JSON in, a loudness-normalized MP4 out. A production harness that layers on top of remotion-dev/skills.
wyc88665-dotcom/media-to-learning-notes/video-to-learning-notes Skill
0★ repoCodex skill for converting media, subtitles, and transcripts into reusable learning notes
CaptainTimmeow/creator-vault-skill/.agents/skills/creator-vault Skill
0★ repoCopy-only local media ingest for creators using a Codex skill
lilingm963/removevideobg-skill/skills/video-background-removal Skill
0★ repoVideo background removal skill for Codex, Claude Code, and agents. Pick the export format, get ffmpeg recipes, and route AI matting to RemoveVideoBG (removevideobg.com).
grischaerbe/fundus-skill/skills/fundus Skill
no license0★ repoAgent skill for managing Fundus assets in Svelte mobile app projects
eligapris/viral-clip-editor-skill Skill
no license0★Agent skill: long video → viral vertical shorts — transcript-first clips, smart crop, captions, transitions.
puntorigen/skills/audio-theater Skill
no license0★ repoLocal-first agent skills for Cursor & other AI coding agents — 100% on your machine, no cloud, no API keys. Apple-Silicon-tuned (MLX/Metal): local image generation, voice cloning, background music, talking-head video, video→3D splat & printable STL, web-action recording, and Word .docx editing.
aiaaaa4/ai-landing-skills/skills/video-download Skill
0★ repoAI落地第四声 agent skills and apps
Yash-Kavaiya/csv-quiz-reels-skills/skills/creative/csv-landscape-video-pipeline Skill
0★ repoHermes Agent skills: CSV practice-test reels (9:16) + landscape quiz videos (16:9) with bulk/resumable pipelines and multi-platform publish metadata.
felipefrf/yt-to-md/skills/yt-to-md Skill
0★ repoTurn any YouTube video into clean, structured Markdown — built for AI agents. No API key, no cost.
natyang1234/auto-edit-video-skill/skills/auto-edit-video Skill
0★ repoPortable reviewed AI video-editing Agent Skill for Codex, Claude Code, Grok, OpenClaw, Hermes, and compatible agents
nanoodlecom/nanoodle-skill Skill
0★Agent Skill: teach your AI agent to build and run nanoodle graphs — multi-model media pipelines as one tool