I Deleted All My Claude Skills… And Claude Got Smarter

🔗 Link do vídeo: https://www.youtube.com/watch?v=XNQBCRcwXV4
🆔 ID do vídeo: XNQBCRcwXV4

📅 Publicado em: 2026-08-12T15:39:14Z
📺 Canal: Nate Herk | AI Automation

⏱️ Duração (ISO): PT11M56S
⏱️ Duração formatada: 00:11:56

📊 Estatísticas:
– Views: 21.989
– Likes: 917
– Comentários: 83

🏷️ Tags:

My playbook for growing a $1M AI agency: https://app.aiautomationsociety.ai/opaa-ads-optin
My FREE resources: https://www.skool.com/ai-automation-society/about?el=claude-delete&hcategory=youtube-videos&utm_campaign=free-group

My Tools💻
FREE MONTH voice to text: https://get.glaido.com/nate
Code NATEHERK for 10% off VPS (annual plan): https://www.hostinger.com/vps/claude-code-hosting

Check out the YC interview with Boris: https://youtu.be/qyPCVqFUyDo?si=4OVk-AqSS62wr7PC

Claude Code may feel worse with Opus 5 because the skills, hooks, and `CLAUDE.md` instructions built for older models can now get in its way.

I break down Boris Cherny's advice, show what happened when I tested Claude with and without my AI OS context, and share the three changes I'm making: simplify old instructions, prompt at a higher level, and give the agent a way to verify its own work.

The goal is not to delete everything. It is to keep the context Claude needs and stop micromanaging how it gets there.

Sponsorship Inquiries:
📧 nate@smoothmedia.co

Connect with me:
https://www.linkedin.com/in/nateherkelman/
https://x.com/nateherk
https://www.instagram.com/nateherk/

TIMESTAMPS
0:00 Why Claude Feels Worse
0:23 Anthropic Deleted 80%
2:05 Delete Your Old Instructions
3:49 My No-Skills Test
5:56 Don't Blindly Copy Advice
7:18 Unhobbling the Model
8:46 Goals and Verification
11:31 Final Thoughts