Open source your playbook or lock it? The experts we onboard keep landing on different answers.

We're building Expertise, a platform where GTM experts publish their playbooks as skills that businesses run on their AI agents, and there's a debate that comes up with every expert we onboard: should a skill be open or locked?

Before building, we looked at why prompt marketplaces and open skill catalogs kept dying. A playbook written as text is just a string, and a string gets copied the moment it's worth copying. And there's a newer twist: ten years ago you open-sourced for other humans, who fork you, cite you, hire you. Now the biggest consumer of an open playbook is the AI itself. Every framework posted publicly becomes something an agent runs tomorrow with your name stripped off. You're not sharing with a community anymore, you're training your replacement one prompt at a time.

So we made protection the default (skills can be installed and run but never opened or copied), with a per-skill choice to open-source instead. I expected everyone to lock. They don't. Some open a skill as a lead magnet and lock the deep stuff behind it, others lock everything, and a few open everything. Openness keeps getting used as marketing, protection as the business model.

Curious where makers here land: does open source still mean what it used to when the main reader of your work is a model? Would you still open your best work if people could use it without copying it?