76 items · Skills 32 · MCP 39 · Plugins 3 · CLI 2
Video & editing
Editing, captions and generated shots: from raw footage to a finished reel.
What you can make
- 9:16 reel with captions
- product video
- animated intro
- talking avatar
With search, filters and ratings.
Ready-made packs
Ready-made tool sets for this task. Load any of them in your AI with one command.
- 9:16 reel with captions
A vertical 9:16 reel from raw footage: the best moments without pauses, balanced audio and animated captions.
/captioned-reel
All items (76)
Skills (32)
Writes video in HTML and renders it to MP4: animations, captions, overlays, voiceover.
React videos with Remotion: compositions, animations, captions, maps and rendering.
Edits raw footage into a final video: cuts fillers and pauses, fixes color, adds captions.
Summarizes YouTube, Bilibili and TikTok videos and podcasts, with chapters and transcripts.
A video studio in Claude Code: script, voiceover, music, AI clips and Remotion render.
Teaches Claude motion design in Remotion: animation, B-roll, captions, transitions and sound.
Picks fal.ai models and runs video production: shots, prompts, ads and motion graphics.
Local editing via FFmpeg: cutting, 9:16 crops, captions, silence, loudness and checks.
Generates and edits video with Gemini Omni Flash from text, frames and reference media.
Makes a promo video for an app from its code: components, script, music and effects.
Creates HeyGen avatars, AI presenter videos and video translations.
Generates video and images in Higgsfield: Veo, Kling, Seedance, ads and thumbnails.
Teaches the agent to work in invideo: generation, media, timeline and project transfer.
Creates Manim math animations with narration, subtitles and a review viewer for revisions.
B-roll timed to speech, subject cutouts, product explainers and sound effects.
Makes a motion graphics music video from a song and a prompt: characters, animation, rhythm.
15 skills for launch-grade motion graphics: launch films, charts, 3D titles and reels.
An open-source agentic video production system: from research and script to edit and render.
Videos in two styles made entirely in code: watercolor animation and kinetic typography.
Remotion Motion Graphics Skills
Remotion skills for motion graphics: kinetic text, camera moves, terminal demos and articles.
Helps build the Runway API into apps: video models, characters, recipes and workflows.
Writes Seedance 2.0 prompts: @ references to media, camera language and templates.
Plans shots and writes Seedance 2.0 prompts: camera, lighting, characters and continuity.
Makes product promo videos in Remotion from your own pages: tuned shots, cut to the beat.
Turns images, SVGs, sketches or a script into a hand-drawn whiteboard animation.
YouTube Skills (TranscriptAPI)
Fetches YouTube transcripts, searches videos and browses channels and playlists.
Teaches the agent to prompt FLUX models and use the Black Forest Labs API for images and video.
Voiceover, transcription, sound effects, music and dubbing via the ElevenLabs API.
Skills for Autodesk Maya: modeling, rigging, skinning, XGen, nCloth, lookdev and rendering.
Motion design for agents: timing, easing, choreography and Disney’s 12 principles in UI.
Turns text into speech locally (Kokoro) or in the Noiz cloud, with timing and voice control.
Creates songs, instrumentals, loops, sound effects and voiceovers with the Venice API.
MCP (39)
Controls DaVinci Resolve: projects, timeline, media pool, color, markers and rendering.
adb-mcp (Premiere Pro, After Effects)
Controls Premiere Pro and After Effects (plus Photoshop) through app plugins and a local proxy.
Edits video in Concat, a free CapCut alternative: timeline, captions, effects, export.
Makes video ads from a description, a product link or a reference ad.
Veo, Gemini Image, Lyria, Chirp and Gemini TTS from Google Cloud as agent tools.
Creates talking-avatar videos, translates videos and runs the HeyGen Video Agent.
Edits in the invideo cloud editor: timeline, color, audio and media generation.
Renders videos in JSON2Video: templates, media, status checks and JSON validation.
Uploads footage to Kapwing, pulls exports, adds subtitles, translates and dubs.
Uploads videos to Mux, manages live streams and reads Mux Data analytics.
Generates video and images with Runway and partner models (Gen-4.5, Veo, Kling).
Composes, edits and renders videos in the Shotstack cloud from a plain-language description.
Cuts pauses and repeated takes from talking-head recordings inside a CapCut project.
Indexes videos and finds scenes by description or image; summarizes and analyzes footage.
Builds CapCut and Jianying projects: captions, PiP, voiceover, filters, keyframes.
Creates talking-avatar videos in VEED Fabric: character, voice and script.
Manages your Wistia account: videos, folders, channels, captions, webinars and stats.
Fetches transcripts of YouTube videos and Shorts, with timestamps and without sponsor segments.
Downloads video, audio, subtitles and metadata from YouTube and other sites via yt-dlp.
Transcribes recordings, identifies speakers, translates and summarizes with AssemblyAI.
Generates and edits images and video with Bria models trained on licensed data.
Reads text aloud in Cartesia Sonic voices, transcribes audio, clones and localizes voices.
Objects, parameters, meshes and materials in Cinema 4D 2026.4+ with no separate install.
Removes noise, filler words and silence from recordings, with a transcript and show notes.
Controls ComfyUI from chat: generates images and video, builds workflows and downloads models.
Edits audio and video in Descript through Underlord prompts, then publishes and exports.
Finds licensed music and sound effects, cuts tracks to length and creates AI voiceovers.
Over 1,000 fal.ai image, video and audio models: pick, check prices and generate in chat.
Separates vocals, instruments and dialogue from audio or video and syncs lyrics.
Runs Gladia transcriptions with diarization, translation, subtitles and summaries.
Controls Houdini: creates and modifies nodes and runs Python code in the scene.
Creates and refines animations from a description or SVG artwork and exports them to Lottie, MP4 and WebM.
Speech synthesis, voice cloning and voice design, plus images and video from MiniMax models.
Generates and streams royalty-free music cleared for commercial use and searches a ready-made library.
Searches, compares and runs models from Replicate: images, video and audio.
Generates images, video, audio and 3D models through the Runware API, with pricing and model picking.
Generates images, video, audio, textures and 3D assets: over 750 AI models plus your own.
Searches YouTube videos and channels, fetches transcripts and finds creators.
Schedules Zoom meetings, generates summaries and automates work with your account.
Plugins (3)
Lets Claude Code watch a video: frames via ffmpeg and a timestamped transcript.
Manages Cloudinary images and video: uploads, transformations, AI analysis, automations.
Photoshop, Firefly, Express, Lightroom and Premiere tools, controlled from chat in Claude.
CLI (2)
MiniMax in the terminal: Hailuo video, images, speech, transcription, image descriptions.
Deepgram transcription, speech synthesis and audio analysis straight from the terminal.