Generate AI UGC ad clips with a Claude skill
A custom Claude skill runs the pipeline: Gemini for talking heads, Kling for B-roll, Higgsfield and Nano Banana for images.
Real AI agent use cases, with sources and setup prompts
Clips, shorts, music videos, podcasts and channels made with AI agents and tools. 48 use cases, newest first.
A custom Claude skill runs the pipeline: Gemini for talking heads, Kling for B-roll, Higgsfield and Nano Banana for images.
Use Opus Clip or CapCut to cut the long episode into clips, with an AI model picking the best moments and writing hooks.
Claude brainstorms 50 ideas and drafts, he edits for voice, Midjourney makes visuals, Buffer schedules and a dashboard tracks results.
Built two video editing systems with Claude Code, one for faceless channels and one for talking-head videos.
Shares an n8n workflow that produces the fast brain-rot video format used on TikTok and YouTube Shorts.
A musician writes the lyrics himself, produces the song in Suno and designs the characters in Midjourney.
Runs Opus 5.5 in Claude Code as editor-in-chief over nine skill sets that cover topics, writing, visuals, video editing, sound and scheduling.
Claude wrote the script, Codex drew 13 faces and Chatterbox cloned his voice from 11 seconds of audio.
Used Claude to plan the channel, research the facts and write scripts for stick-figure stories about the history of money.
A YouTube Desk bot applies his listing packs in YouTube Studio: titles, descriptions, tags, end screens, cards and Shorts uploads, all private until he approves.
Built a pipeline in one Claude Code session: five parallel research agents with every claim sourced, then plain-English narration.
Combine Midjourney, Runway, Kling and Suno to make music videos, commercials and short scenes.
Got ChatGPT and Claude to write LDraw, the format for Lego models, and built an open-source Lego generator.
Take Midjourney stills and a Suno track, animate the stills with Kling, and have an AI model beat-track and edit to the lyrics.
Write the script, generate narration in ElevenLabs, use voice replacement for lip sync, then finish in your video editor.
Upload an EPUB to Spotify's audiobook tools, pick an ElevenLabs voice, fix pronunciation and publish.
A Grok Bot producer takes an X article link, voices it with ElevenLabs, makes art with Grok Imagine and uploads the episode to YouTube.
After a $137 Adobe cancellation fee, built AIVidMaker, an open-source editor that Claude Code, Codex, Cursor or Grok Bot can control.
Combined Suno for audio, Google ImageFX for the character, HeyGen for lip sync and CapCut AI for B-roll transitions.
Used Epic's MCP server and Claude Code plugin for Unreal Engine 5.8 so AI models drive the editor, and vibe-coded a character for his game.
Built an automated video generation pipeline with Claude Code and Remotion.
An agent pipeline generates video ideas with ChatGPT and renders the scenes with Veo 3 through the FAL API, with no manual editing.
Built a Claude Code tool to write every prompt with structure, character consistency and content-filter checks, then generated the film with Higgsfield and Seedance 2.0.
Made an MCP server so Codex can do anything in Ableton Live while the author was stuck holding a sleeping baby.
Uses Gemini's native video embeddings to search raw footage with plain text queries such as a car cutting you off, with no transcription.
Built Time Portal: you are dropped into a historical moment shown as AI video and guess where and when you are.
Clone your voice in ElevenLabs and use it for narration, approving every cut yourself.
A creator shows live how Claude Code is replacing Opus Clip for making his video content.
Speak the whole job out loud with Wispr Flow before opening a model; talking makes lazy prompts harder.
Shipped a browser extension and made a 17-second animation of the old popup turning into the new one to announce it.
Grok Bot watches his X timeline, works out why other posts take off and drafts his next one.
A Grok Bot plans each shoot: camera angles, talking points, SEO titles, how to cut Shorts, and filming rules to check.
Built RxFilm Studio, a workspace where an AI agent creates and edits product videos from your requests.
Test brand: Adobe Firefly's assistant produced a logo, vector file, brand kit and four mock-ups for a made-up brewery.
Dictate a first version with Wispr Flow, then ask AI to fix punctuation and squeeze it under 280 characters. Ideas stay your own.
Explained his video editing process in detail, then let Grok Bot take over the computer to do the edits.
A game developer asked Grok Bot to open his custom art-generation webpage and produce art assets for his game.
Drew a character of his daughter, vectored and coded it in Claude Code so it bounces and says hi when tapped.
Moved his video ad production into a Claude Code workflow.
Got DeepMind's open Magenta RealTime music model running on an iPhone without the GPU after it was said to run only on Mac.
Built a CLI that turns plain-English requests like converting to a GIF into the right ffmpeg commands.
Built an AI search over every photo and every frame of video stored on a Mac.
Produced a Pixar-style 3D animated piece with AI tools in one day.
Generated a 30-second video intro from one still image and a prompt; the face, voice and room are all AI.
Used AI to rework three albums his college band recorded 25 years ago.
AutoShorts is a local, GPU-accelerated AI pipeline that turns long videos into short-form clips.
Used AI to recreate a $4,000 piece of audio hardware as a software plugin from schematics, patents and ROMs.
Vibe-coded a free in-browser alternative to Screen Studio for polished screen recordings.
Five real AI use cases with setups, every morning. Free.
The Daily 5 will arrive in your inbox each morning. Unsubscribe any time.
Send the public link (post, video, repo or write-up). We credit you and link back.