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,…
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…
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
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…
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, …
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…
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…
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. …
Productivity
minutes-video-review
Analyze a product walkthrough, bug report video, Loom, or ScreenPal using Minutes transcription plus visual review. Use when the user wants a recorded demo or bug clip turned into …
Automation
kie-ai-video-production
Manages video, image, and audio generation through the Kie AI platform. Recognizes all available models, selects appropriate ones, and orchestrates multi-step pipelines for product…
Automation
agency-meetup-publish
End-to-end pipeline for publishing AGENCY Community meetup recordings to YouTube. Downloads the Zoom recording, adds intro and outro, generates a thumbnail, creates a description w…
AI / ML
free-image-and-video-generation
Free local AI image and video toolkit with cloud generation. Local tools handle upscale, face enhancement, background removal, object erase, face swap, segmentation, and media proc…
Content
video-studio
Handles end-to-end video creation and editing from script to finished MP4, including auto-cut, jumpcuts, captions, and platform-specific polishing. Uses local FFmpeg by default wit…
Content
video-compose
Creates short videos on the filmmaking canvas using the local generate_video.js CLI. Follows canvas-aware rules for prompts, reference assets, and provenance when animating charact…
Automation
omd:batch-launch
Adds ten brand references at once, syncs document counts, and generates a hyperframe-based promo MP4. Increments reference count by ten per run and produces one gitignored video as…
Content
generate-script
Call the project's configured text model to produce a JSON script, including image_prompt and video_prompt for each storyboard. Reads intermediate files from step1 and project.json…
Content
li-opening
Activates on requests to optimize openings, craft hooks, or improve intros in video scripts. Performs quality and audience-perspective checks before generating 10-15 opening option…
Automation
colab-video-pipeline
Manages the Jiang Lens Colab video pipeline for YouTube downloads, diarization, transcription, Drive sync, and Playwright automation. Requires the jianglens Drive folder and never …
Content
libtv-video
Create images and videos using Seedance 2.0 via LibTV Gateway. Supports text-to-video, image-to-video, style transfer, and models including Kling 3.0, Wan 2.6, and Midjourney. Trig…
General
videodb
Ingest, index, and edit video and audio from files, URLs, or live streams. Build visual and spoken indexes, search with timestamps, edit timelines, add overlays or subtitles, gener…
Content
gif-maker
Create short looping GIFs from video. Convert existing MP4s with palette optimization or generate brief clips via video providers then export as GIF. Supports common aspect ratios …
Content
video-content-strategist
Plans video content strategy, writes scripts, optimizes YouTube channels, and builds short-form pipelines for Reels, TikTok, and Shorts. Use for repurposing long-form content into …
Content
ecom-shoe-image-shotlist-github
Footwear e-commerce photography expert. Analyzes product images, selects scenes, and generates six advertising-quality hero shots plus optional video in a parallel pipeline coverin…
AI / ML
dream-to-video
Converts dream descriptions, diary excerpts, or spoken dream content into video. Detects phrases like "dream to video" or direct dream text and transforms them into prompts for vid…
Content
newsletter-to-video
Repurpose a newsletter issue into a high-level YouTube video outline. Use when asked to create a YouTube outline from a newsletter, turn a newsletter into video, or convert any new…
Content
wjs-dubbing-video
Generate time-aligned TTS voice dub for a video using a target-language SRT. Routes by voice ID (Volcano for Chinese, edge-tts for others). Outputs dubbed MP4 and hands final mixin…
Automation
llmer-demo
Execute browser or terminal automation scenarios with video recording from natural language descriptions. Use for generating demo videos, capturing HAR files, recording CLI demos, …
Content
ad-video
Generate platform-optimized video ads from a product brief. Supports brand kits, six ad types, six platform formats, batch personalization, A/B variants, stock footage, screen reco…
Automation
video-subtitle-translator-agent
Extracts embedded subtitles from video files, translates SRT/VTT tracks, and re-embeds localized versions. Supports batch processing, language detection, and bidirectional text han…
Content
remotion-render
Render MP4 video from React or Remotion TSX source code. Accepts component code and returns rendered output using the full Remotion API including useCurrentFrame, useVideoConfig, s…
Content
remotion-render
Render MP4 video from React or Remotion TSX source code. Accepts component code and returns rendered output using the full Remotion API including useCurrentFrame, useVideoConfig, s…
Content
remotion-render
Render MP4 video from React or Remotion TSX source code. Accepts component code and returns rendered output using the full Remotion API including useCurrentFrame, useVideoConfig, s…
Content
remotion-render
Render MP4 video from React or Remotion TSX source code. Accepts component code and returns rendered output using the full Remotion API including useCurrentFrame, useVideoConfig, s…
Automation
wjs-burning-subtitles
Burn subtitles into video pixels or soft-mux as a togglable track. Handles final composite step for localization: burn subs, mix dub track, and keep original audio as low-volume be…
Content
video-directing
Applies cinematic directing principles from masters like Spielberg, Cameron, and Nolan to AI video generation. Focuses on visual storytelling, emotional pacing, shot composition, a…
Automation
krillinai-pipeline
Plans multi-stage KrillinAI CLI workflows such as subtitle generation plus TTS plus horizontal or vertical rendering. Pipeline execution remains a reserved surface unless implement…
Content
wjs-converting-text-to-video
Convert a 王建硕-style WeChat article into a narrated short MP4 video using TTS voiceover, HyperFrames CSS/GSAP animation, subtle SFX, and abstract watercolor background. Outputs 1080…
AI / ML
face-swap
Swap faces or characters into video or images by routing across animation, editing, and motion-control models based on single still vs video, full character vs face only, or dialog…
Content
stitch-remotion
Creates walkthrough videos from Stitch projects by downloading screen screenshots, assembling Remotion compositions with transitions and overlays, and rendering to MP4 using screen…
AI / ML
arch-v
Orchestrates video production workflows for Veo 3. Guides prompt creation via text-to-video or image-to-video pipelines, validates completeness, and integrates camera movements and…
Content
content-engine-cinema
Apply cinematic generation standards including start-frame doctrine, camera vocabulary, node pipelines, scene formulas, and 25+ design styles. Supports Higgsfield CLI models for pr…
Content
cut
Builds a cut from a library—scene, selects, roughcut, or custom task. Asks what kind of cut is needed, collaborates to define the output, and exports a file for Final Cut, Premiere…
Content
ai-avatar-video
Produce AI avatar, talking-head, and lip-sync videos using audio-driven and multi-modal models. Selects appropriate model and prompting patterns for UGC, virtual presenters, or dub…
AI / ML
openai-latam-audiobook
Build a complete audiobook pipeline: translate Russian text to Argentine Spanish with GPT-4o-mini, generate TTS, and produce video with background image. Auto-scales parallelism by…
AI / ML
video-understand
Analyze video content, understand motion and temporal sequences, extract frame information, describe scenes, and perform video-based AI analysis on common formats including MP4, AV…
Testing
debug-video
Extract key frames from screen recordings to analyze UI bugs over time. Detect animation glitches, race conditions, gesture issues, scroll jank, keyboard overlap, and navigation tr…
Content
video-summarization
Summarizes video content by routing short clips to a VLM endpoint and longer videos to a dedicated microservice. Use for analysis, description, or troubleshooting the summarization…
AI / ML
agent-tools
Access 250+ AI services through inference.sh including image and video generation, LLMs, search, 3D rendering, and social automation with models such as FLUX, Veo, Gemini, Grok, an…
AI / ML
agent-tools
Access 150+ AI services through inference.sh including image and video generation, LLMs, search, 3D rendering, and social automation with models such as FLUX, Veo, Gemini, Grok, an…
AI / ML
agent-tools
Access 250+ AI services through inference.sh including image and video generation, LLMs, search, 3D rendering, and social automation with models such as FLUX, Veo, Gemini, Grok, an…
AI / ML
ai-video-generation
Generate AI videos on RunComfy via the runcomfy CLI, routing across HappyHorse, Wan-AI, ByteDance Seedance, Kling, Google Veo, and other models for text-to-video and image-to-video…
AI / ML
venice-video
Create and transcribe videos with Venice. Supports async quote-queue-retrieve flow, text-to-video, image-to-video, upscale, reference images, scene control, and YouTube URL transcr…
Content
video-edit
Routes video edits to the appropriate model on RunComfy for restyling, motion transfer, or background swaps while preserving identity. Matches intent to Wan, Kling, or Lucy edit mo…
Content
视频创作助手
Generates professional animated videos with the Remotion framework. Supports product demos, tutorials, data visualizations, marketing clips, and explainer content from text or conc…
Testing
ui-demo
Records polished UI demo videos using Playwright with visible cursor, natural pacing, and professional quality. Use for walkthroughs, screen recordings, or tutorial videos of web a…
Content
video-editing
Provides AI-assisted video editing workflows using FFmpeg, Remotion, ElevenLabs, and CapCut. Covers cutting, structuring, and augmenting real footage from raw capture to final poli…
Showing the top 60 of 550. See the full list →