Video in Content & Creative

Create, edit, and optimize Claude skills with performance testing and benchmarking.

Create generative art with p5.js using algorithms, randomness, and interactive parameters.

Generate music, voiceovers, and sound effects as audio files.

Generate and edit images from text descriptions using AI.

Generate and iteratively edit images from text descriptions.

Guide teams through organizational changes using the ADKAR model and communication strategies.

Create PowerPoint presentations with smooth cross-slide animations and shape continuity.

Generate, edit, and refine images from text prompts with design templates.

Turn a product photo and brand brief into a cinematic 5-10 second product ad. Needs a MuAPI key.

Build a short AI music video from a song theme — keyframes, animation, and matching music. Needs a MuAPI key.

Generate one continuous cinematic shot — no cuts, one flowing scene with dramatic lighting and motion. Needs a MuAPI key.

Generate high-fidelity video with Seedance 2.0 — text-to-video, image-to-video, first/last frame, and consistent characters. Needs a MuAPI key.

Generate cinematic video directives for AI video models using creative intent.

Convert long videos into viral-ready short clips ranked by engagement potential.

Generate GIF and MP4 demo videos from terminal recordings and screenshots.

Extract transcripts from YouTube videos with optional timestamps.

Recommend proven image generation prompts from a library of 10,000+ for any AI model.

Generate or edit images using OpenAI's image models.

Embed HTML visualizations directly in chat messages without opening panels.

Turn a topic into a narrated 4K explainer video with script, voiceover, and music.

Review architecture specs and design docs using multiple independent AI reviewers to surface consensus issues.

Create, edit, and analyze PowerPoint presentations and slide content.

Detect AI-generated audio, images, video, and text to identify deepfakes and synthetic media.

Download videos from YouTube and other platforms for offline viewing or editing.

Turn any topic into a finished paper-collage explainer video with voice-over, music, and captions.

Transcribe audio and video files to text with fast local or remote processing.

Repair broken line wrapping in Claude Code exported conversation files.

Diagnose and fix plugin installation, enablement, and activation problems.

Recover context from interrupted Claude sessions and continue work without replaying full history.

Configure custom statuslines for Claude Code with token counts, costs, and git status.

Extract Mermaid diagrams from markdown and convert them to PNG images.

Compress images to WebP or PNG format with automatic tool selection.

Format plain text into well-structured markdown with proper headings and emphasis.

Generate photoreal or designed images with OpenAI's GPT-4 vision model.

Mix narration audio over video, adjust levels, and add subtitles.

Assemble video clips from a plan into a single edited video file.

Generate a Chinese-narrated recap video from your input video automatically.

Generate timestamped Chinese narration scripts for videos with validation.

Convert text and documents into natural-sounding audio or podcasts.

Write, adapt, and break down screenplays into shot notes and character details.

Organize canvas nodes into semantic groups with labeled frames for clarity.

Generate and edit filmmaking images for characters, locations, storyboards, and video production.

Generate cinematic AI video prompts for Sora, Kling, and other video models.

Download videos and audio from 1500+ websites with custom resolution, subtitles, and playlists.

Create, edit, and export video timelines with AI voiceover and subtitles.

Design album artwork concepts and generate AI art prompts for your music.

Generate YouTube video ideas for any topic and save them to Airtable.

Generate authentic character behavior and performance direction for video prompts.

Discover and use pre-built one-click workflows for content creation, video generation, and more.

Learn to use Higgsfield's AI copilot and optimize your platform credits.

Write and refine video and image prompts for Higgsfield AI models.

Transcribe media, create subtitles, edit talking-head videos, and export clips from the command line.

Publish meetup recordings to YouTube with intro, thumbnail, and timecodes.

Find and install AI art models from Civitai into ComfyUI locally.

Train custom LoRAs for WAN video models and Z-Image with local or cloud setup.

Generate anime and manga artwork from text descriptions and Danbooru tags.

Extract and save timestamped transcripts from YouTube videos as text files.

Edit short-form videos for multiple platforms with automated transcription, syncing, and multi-platform exports.

Search transcripts and find what was said in videos, podcasts, and conference talks.

Generate images, videos, music, and audio from the terminal with social media automation.

Create animated videos by writing HTML, CSS, and GSAP timelines.

Deprecated skill; use Media to Transcript instead for video and audio transcription.

Burn subtitles into video or add them as toggleable tracks in one encoding pass.

Convert articles into narrated short videos with animations and effects.

Create, edit, and caption professional videos with AI avatars, generated footage, and music.

Create cinematic motion videos and animated promos from text, images, or web content.

Write ready-to-use image prompts for Nano Banana and GPT Image 2 — covers, posters, product shots, storyboards, and image-to-video start frames.

Turn an idea into a director-grade prompt for any AI video model — Veo, Kling, Sora, Runway, Luma, Seedance — with shot lists, camera, and pacing.

Generate, upscale, and edit images using AI with multiple quality and cost options.

Generate videos from text prompts or images using AI.

Generate and edit images with text or reference images using Gemini's native models.

Generate automation scripts for browser agents to bundle multi-step interactions efficiently.