Everyone's building "AI agents." I just built mine out of folders. No new platform, no dashboard. Just a root folder, one subfolder per department, and a framework (FFPP: Folders, Files, Processes, Permissions) that any CLI agent like Claude Code or codex can work inside of straight away. - Every folder gets its own instructions file + its own credentials + its own reusable "skills" - Runs entirely on your own device. Nothing to host, nothing extra to pay for Video 1 : Just the concept. Next one, I build the whole thing live from an empty folder. If you have any question, ask me in the comments section.

Context: putting one arrow on a screenshot meant three apps for me. GoFullPage to capture, Annotly to annotate, then paste it wherever it was actually going. Every single time. What kept me in that loop wasn't the steps. It was assuming that building the alternative would be a project. It was about 30 minutes in Claude Code. Now it is one shortcut. Full page capture and the editor in the same place, running on my own machine, nothing uploaded anywhere. One thing worth taking even if you never build anything: If you blur client information in screenshots, use a solid bar rather than pixelate. Pixelated text can often be recovered when the font and the pixel grid are guessable. A solid bar replaces the pixels, so there is nothing underneath to pull back out. The interesting part is that I didn't start with the idea of building a product. I just had a problem that annoyed me, so I built a small solution for myself. The bigger idea: Look at the boring things you repeat every day. - Moving information between tools? - Downloading something and uploading it somewhere else? - Doing the same manual steps over and over? Maybe that's something you can build yourself.

I run a UK digital agency and one of my clients is a builder who sends me raw build project videos via WhatsApp. We turn these into branded shorts and reels for YouTube, Instagram, Facebook, and Nextdoor. Current setup ($100/month): My VA in Nigeria handles the whole pipeline manually: • Downloads videos from WhatsApp • Runs them through Descript (adds voiceover when client’s ops manager hasn’t recorded one) • Polishes clips in Opus Clip Pro • Adds logo and branding • Writes captions • Schedules to YouTube, Insta, Facebook • Manually posts to Nextdoor via GHL workspace He’s reliable, the quality is OK, and at $100/month it’s hard to beat on cost. The AI-automated alternative I scoped: Make.com + Claude API + Creatomate (branding) + ElevenLabs (voice clone) + Opus Clip Pro API + GHL scheduling. Roughly £60-75/month in tooling, plus probably 20-30 hours of build time on my end. The build would handle: WhatsApp ingestion, Claude analysing each video and writing platform-specific captions, voiceover generation when needed, automated clipping, branding overlay, scheduled posting across all platforms, with one approval gate before publishing. Where I’m stuck: On paper the AI route looks cheaper long-term, but when I actually compare: 1. My VA costs $100/month flat, no build time, no API surprises, deals with edge cases naturally 2. The AI stack is ~£60/month in tools but needs my time to build and maintain, and breaks when APIs change or videos are unusual 3. Nextdoor still needs a human click either way (no API) 4. Voice cloning needs careful setup and consent 5. The VA can also handle other ad-hoc tasks the AI can’t My questions for the group: • Has anyone built something similar and found the maintenance cost was higher than expected? • Is there a hybrid worth considering — AI for the captions and Claude analysis, VA for the video editing and posting? • Am I overcomplicating this when a good VA with the right SOPs is genuinely the more cost-effective answer?

- Open the Claude desktop app → Cowork - Click + → Record a skill, grant screen recording permissions and click Start Recording - Perform a task you repeat often, from start to finish and narrate it to Claude Sample Prompt (Narration): While recording your skill, say something like this out loud: I'm doing [TASK] to achieve [GOAL]. First, I [ACTION] because [REASON]. Next, I [ACTION] so that [OUTCOME]. If [CONDITION] happens, I [ALTERNATIVE ACTION]. This is the most important rule: [RULE OR DECISION]. Ignore any clicks or tabs that aren't part of this workflow. When the task is complete, verify that [SUCCESS CRITERIA]. - Claude packages it into a saved skill - Open a new chat and run it using /your-skill-name - To automate it, ask Claude to schedule the skill Automation Prompt: Let's make this a scheduled task. Ask me when it should run, then create the schedule for me.

Hi! Welcome to the Content Academy. This community is designed to help you build a profitable content strategy, efficient team & automated content process. Step 1: Introduce yourself in THIS THREAD below! (✄ copy/paste template 👇) Where are you from? What are you working on? What immediate help do you need? Step 2: Read the rules and checkout our free courses and paid programs