Activity
Mon
Wed
Fri
Sun
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Memberships

Agent Lab

211 members • Free

Claude FR

1k members • Free

Claude Code Academy

799 members • Free

Claude Community -Deutsch

179 members • Free

Claude Code Architects

1.2k members • Free

OpenClawBuilders/AI Automation

490 members • Free

Openclaw Labs

1.9k members • Free

OpenClaw Install & Support

147 members • Free

AI - OpenClaw - Code

405 members • Free

2 contributions to Oleg's AI Lab
🚀 My Claude Code System For Viral TikTok Videos
I built a system with Claude Code that tracks your TikTok competitors, finds their most viral videos, and generates content ideas + scripts you can film right away. No more guessing what to post. No more staring at a blank screen. You add your competitors → the system scrapes their best content → AI analyzes the patterns → you get 5-10 video concepts tailored to your niche. Each one comes with a hook, structure, and CTA. It runs as a web app on your laptop. The whole thing was built with Claude Code. 👉 GitHub repo: https://github.com/melnikoff-oleg/tiktok-ai 👉 Full step-by-step install guide attached below — covers VS Code, Claude Code, API keys, and running the pipeline. If you get stuck, drop a comment. I'll personally help you get it running.
1 like • 5d
Cool system. The part that usually breaks on TikTok competitor pipelines is the scraper side: TikTok runs aggressive anti-bot + device fingerprinting, so even good HTTP clients get 403'd or rate-limited after a few pulls. If you're hitting that (or when someone tries to scale this to 50+ competitor accounts), browser-act (https://github.com/browser-act/skills) as a Claude Code skill handles the stealth browser + captcha bypass piece. I've used `browser-act navigate` + `browser-act eval` to pull TikTok metadata without the blocks. Drops into the scraping step, so you keep your pattern analysis and script generation pipeline as-is.
We built this using Claude Code + Supabase… and law firms are loving it 🔥
We've been working on connecting AI directly with legal case management — not just to track cases, but to actually automate the entire client follow-up process. Here's what we built: ✅ AI-powered Case Pipeline Dashboard ✅ Automated client follow-up emails based on case stage ✅ Deadline risk flagging from document content ✅ Role-based access for Partners, Associates & Paralegals ✅ Everything managed from one clean interface Instead of juggling spreadsheets, email threads, and a 10-year-old CRM… everything is now streamlined into one system. This is not just a concept — it's live and working. The goal is simple: 🎯 Zero missed hearings 🎯 Follow-ups that run without human input 🎯 Let AI handle the admin so attorneys can focus on cases If you're running a law firm or legal practice, this kind of system is a game changer. 💬 Comment "legal" and I'll show you the demo + full breakdown.
We built this using Claude Code + Supabase… and law firms are loving it 🔥
1 like • 5d
Nice build; the deadline risk flagging is where most demos fall apart and you shipped something a firm would actually pay for. One scaling thought: a lot of court/docket/e-filing portals (PACER, state registrars, local court sites) only expose hearing dates and filings through their browser UI with no API. If you're adding external docket ingestion next, I've been using browser-act (https://github.com/browser-act/skills) as a Claude Code skill that gives Claude Code `navigate` / `eval <js>` / captcha handling on sites like that. Pairs with what you already have: Supabase for state, Claude Code for extraction logic, browser-act as the 'reach out to no-API sites' piece.
1-2 of 2
Maggi Cc
1
3points to level up
@maggi-cc-1001
I'm Maggie

Active 4d ago
Joined Sep 23, 2025
Powered by