Content
短视频口播文案 Spoken Script
This skill is used to guide the AI in generating short video spoken scripts with high contrast, strong resonance, a sense of story, and personal IP attribute...
Design
分镜图工作流 Storyboard Workflow
A professional storyboard skill for film, advertising, short video, and educational narrative scenarios, built around a strict 'plan first, render later' flow.
Data
抖音数据分析 SocialDataX 作品搜索
用于抖音数据分析、抖音热榜、抖音作品搜索、图文搜索、关键词检索、内容调研、竞品分析和趋势研究。覆盖 Douyin hot search and work search，来自 SocialDataX 社媒数据助手。
Productivity
loom-analyzer
Read Loom videos — pull the transcript, pick the moments that matter for the task at hand, and extract still frames as visual proof. Use whenever the user provides a Loom URL (loom…
Content
agente-anuncios-influencer-ia
Agente para crear anuncios HABLADOS con un personaje/influencer IA (existente como Kassia, o uno nuevo creado desde cero) — guion dividido en escenas por conteo de palabras, imágen…
AI / ML
factorized-video-gen
Factorized video generation pipeline based on arxiv:2512.16371. Decomposes text-to-video into three stages: (1) LLM reasoning to rewrite prompts into first-frame captions, (2) T2I …
Content
ai-media-generator
為使用者產生高品質的 AI 生圖、生影片、生音樂提示詞，並在需要時透過瀏覽器自動化實際送到目標平台。涵蓋 OiiOii、Kling 3.0/O-series、Seedance 2.0 pro、Suno v5.5、Seedream 5.0/4.0、Vidu Q3、Midjourney V8.1、Flux 1.1 Pro / Kontext、Runway Gen…
Content
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seed…
Content
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seed…
Content
lyric-video-director
Use when creating a stylized lyric video from a song file, lyrics, and rough lyric timings. Directs the complete workflow: normalize timings, analyze musical gaps and song structur…
Data
dy-note
DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes…
AI / ML
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand-…
Content
yt-master
Plans, scripts, packages (title + thumbnail), and optimizes YouTube videos by merging two proven methodologies: Caique Pereira’s embrulho-primeiro approach and Camilo Coutinho’s 20…
Content
script-to-video
Full pipeline — topic/script/text file → OmiVoice TTS (Prince's voice) → Whisper word-level timestamps → HyperFrames synced video composition. Use when asked to "make a video about…
Content
analyze-video
Use when the user wants to analyze one or more videos (URLs or local files) and produce a Word document with embedded frames and a written timestamp-based analysis. Triggers on "an…
Design
cinematic-hyperframes
Cinematic motion design workflow for Hyperframes/Hyperframer and HTML-to-video product films. Use when creating or revising SaaS, app, ecommerce, launch, social, or brand videos th…
General
ads-youtube
YouTube Ads analysis covering campaign types, creative quality, audience targeting, and measurement. Evaluates video ad performance across skippable, non-skippable, bumper, Shorts,…
AI / ML
video-analyzer
Analyzes a video file with Google Gemini and returns a structured markdown report covering top-level summary, scene-by-scene breakdown, audio transcript (or honest "silent" note), …
Content
ugc-ad-meta
Genera anuncios UGC (User Generated Content) para Meta Ads desde un brief en lenguaje natural. Crea persona realista hablando a cámara con lip-sync, audio nativo en español LATAM, …
Automation
xeonupscale
ffmpeg lanczos video upscale skill. Resizes a video to a higher resolution (e.g. 480p→540p, 480p→1080p) using libx264 + lanczos scaler. Bundles a static ffmpeg from BtbN/FFmpeg-Bui…
Automation
watch-local
Watches any video (URL, local, or network share) entirely on-device: downloads via yt-dlp, extracts frames with ffmpeg, and transcribes locally with faster-whisper while validating…
AI / ML
vidu-skills
Generate video and images by calling the official Vidu API via vidu CLI. Use when the user wants text-to-image, text-to-video, image-to-video, head-tail-image-to-video, reference-t…
Content
sketch-to-video
Turn hand-drawn sketches into AI music videos. Guides through extracting sketches, generating style variations, creating video transition prompts, composing a song, and editing a b…
Content
redbox-video-director
Use when generating short videos with RedBox official video API. Produces a detailed shot script first, asks the user to confirm it, then chooses between text-to-video, reference-g…
Content
claude-watch
Watch a tutorial or lecture video (URL or local path) and produce structured study notes. Downloads with yt-dlp, detects scene changes with ffmpeg, pulls a timestamped transcript (…
Content
gptnb-image
Generate images and videos via gptnb.ai. 图像：gpt-image-2 / gpt-image-2-vip(分层) / dall-e-3。视频：seedance 2.0 / 2.0 fast / 1.5 pro / 1.0 系列（doubao-seedance-*）。Use when the user asks to …
Content
Video Ad Script Writer — Moroccan Market Edition
Generates complete video ad scripts for 15s, 30s, and 60s formats in Darija (Moroccan Arabic) with shot-by-shot breakdowns, Islamic compliance guidelines, trend alignment, and cult…
Content
hyperframes
Build video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Handles synced subtitles, text…
Content
notebooklm-superskill
Generate slide decks, audio podcasts, infographics, and video overviews from NotebookLM notebooks. Customizable by audience, format, language (80+), orientation, and visual themes.…
DevOps
video-pipeline-rocm
Builds real-time or batch video inference pipelines using GStreamer with ROCm/CUDA. Handles RTSP, files, or camera input; decodes via hardware acceleration (AMD VCN/NVIDIA NVDEC); …
Automation
transcribe-anything
Transcribes audio and video files to text using configurable ASR backends including local Whisper variants, OpenAI, Groq, Deepgram, AssemblyAI, Gemini, and Hugging Face models. Han…
Automation
lark-vc-agent
Join or leave ongoing Lark video meetings on behalf of a user and capture live events such as participant arrivals, departures, speech, chat, and screen sharing. Use +meeting-join …
Content
generate-video
Guided HiggsField video generation — collects genre, topic, references, model, and duration, then plans a full storyboard, generates a 3×3 keyframe grid for visual consistency, sli…
Content
autocut
Edit video conversationally via AutoCut MCP server inside DaVinci Resolve. Use when trimming by transcript, removing filler words, selecting best takes, or generating subtitles. Tr…
Content
blessing-video-weaver
Assembles a polished blessing or greeting compilation video from per-person speech clips: transcribes Hebrew audio, crafts a thematic script with 30+ woven segments, normalizes lev…
Engineering
shiguredo-vpl
Deep reference for shiguredo_vpl (vpl-rs) crate: Intel VPL 2.17 bindings with static-linked libvpl. Covers H.264/H.265/VP9/AV1 hardware encode/decode, multi-GPU selection, rate con…
Content
music-to-video
Generates beat-synced HyperFrames videos from music tracks or audio sources. One pass analyzes the track, then an orchestrator builds a frame-by-frame plan while sub-agents render …
AI / ML
ai-multimodal
Process and generate multimedia with Google Gemini API. Analyze audio (timestamps, summaries, speech, music up to 9.5h), images (captioning, detection, OCR, Q&A, segmentation), vid…
AI / ML
ai-multimodal
Process and generate multimedia with Google Gemini API. Analyze audio (timestamps, summaries, speech, music up to 9.5h), images (captioning, detection, OCR, Q&A, segmentation), vid…
Content
roughcut
Builds a roughcut YAML and exported XML (Final Cut, Premiere, or Resolve) from an approved plan markdown file produced by cut-planner. Spins up a sub-agent that reads the library, …
Content
vibe-creating-prompt
Evaluates user input for Vibe Creating video style and converts ideas, stories, or rough prompts into optimized single-scene or multi-shot text-to-video prompts while retaining spe…
Web
InVideo AI Clone Project
This is a full-stack application that replicates InVideo AI functionality: - Backend: Node.js + Express with video processing pipeline - Frontend: React + Vite interface for video …
AI / ML
rt-vlm
Integrates with the RTVI VLM microservice on VSS 3.1 for generating dense captions and alerts from stored video or live RTSP streams. Supports file uploads, stream management, Open…
Web
GITHUB COPILOT INSTRUCTIONS
Du bist ein Senior React- und Remotion-Entwickler mit Spezialisierung auf: - Programmatische Videogenerierung mit Remotion 4.0+ - Medizinische Software (DSGVO-Compliance, medizinis…
Content
hooksmith
Audits, builds, and rewrites hook systems for short-form video—Instagram Reels, TikTok, Shorts—including first-frame text, spoken intros, open loops, rehooks, retention paths, and …
Design
beauty-photography-master
Transforms product photos into luxury advertising visuals or short video ads. Handles product identification, creative direction, prompt engineering, campaign generation, visual QA…
AI / ML
voooai
Generates short dramas, webtoons, storyboards, images, and videos from text or reference uploads. Forwards creative requests to a backend workflow engine that handles generation, e…
Design
mira-vertical
Generates a 9:16 vertical deck from a 16:9 Mira source or creates new portrait slides from scratch for Reels, Shorts, and TikTok. Leaves the original untouched, producing index-9x1…
AI / ML
Robot Learning From Video
A Technical Blueprint for Scalable Implementation of Latent Action Pretraining from Videos on HPC InfrastructureExecutive SummaryThis document presents a comprehensive technical bl…
Content
video-shortform
Generates 3-10 second short-form video clips for product reveals, motion teasers, and ambient loops. Works with multiple video models and saves a single MP4 to the project folder. …
Automation
best-youtube-video-editor
Enables conversational AI video editing for YouTube creators: trim segments, add chapters and captions, adjust pacing, and export optimized files using plain-language prompts. Auto…
Content
branded-reel-pipeline
End-to-end premium short-form brand reel creation with on-brand visuals and optional live dashboard data. Includes script generation, branded visuals, voiceover, live-data capture,…
AI / ML
arkcli-gen
CLI tool for Ark image and video generation. Dispatches text-to-image, image-to-image, text-to-video, or reference-based tasks using the active profile's supported models and param…
Content
libtv-video-production
用 LibTV CLI（Seedance 2.0 视频 + nebula/seedream 图）把分镜做成短片（2D 绘本或写实皆可）——涵盖九宫格故事板→clean 去标注→image2video 单镜生成→ffmpeg 本地剪辑(转场+配乐+旁白)全流程，附 prompt 铁律模板库（角色/比例/零文字/场景锁定/负面词反召唤）与高频踩坑速查（多狗/角色…
Content
produce-video
Produces multi-runtime video export bundles from briefs—manifests, shot prompts, scaffolds, and post-production stages—for shortform social or app-preview demos. Emits tool-agnosti…
Automation
mira-slide-to-video
Converts Mira deck slides into MP4 videos by capturing real animations in headless Chrome and stitching with ffmpeg. Selects any slides, supports multiple aspect ratios, applies tr…
Content
embedded-captions
Add captions to talking-head video using 32 visual identities across column-flow and themed engines, with matte occlusion and cinematic compositing. Routes by identity on motion-gr…
Content
spark-video-cast
Generates consistent reference assets for characters, locations, and props—the core elements of visual continuity in video projects. Wraps image generation and editing to produce p…
Testing
remotion-visual-debug
Visual debugging for Remotion video projects. Use when working with Remotion compositions to verify animations, layouts, positioning, and timing by rendering frame samples. Essenti…
Content
social-short-production
Produce platform-ready short vertical videos for TikTok, Reels, YouTube Shorts, and LinkedIn from briefs, scripts, or source media. Handles audience definition, hooks, shot plannin…
Showing the top 60 of 1,175. See the full list →