The blog
Field notes on skills, workflows, and the failure modes nobody documents. Every post is grounded in a real cyberg7 skill you can install today.
Two production sites, two different content sources, one architecture. The diff that proves a good abstraction is smaller than you'd think — and why Anthropic's agent guidance points the same way.
Install the starter pack, let Claude find the right skill for the task in front of you, and ship one change the cyberg7 way — all before your coffee gets cold.
If you paste the same conventions into Claude Code every morning, you are doing setup work a skill should do for you. Here is the fix — backed by Anthropic's own guidance.
Field notes on getting more out of Claude Code: skills, workflows, and the failure modes nobody documents. Start here.
An agent looping on a Stop hook overnight is the failure nobody documents. Here is why it happens, what Anthropic's docs now guarantee, and the one-line guard you still need.