[throw-10-13]

Architectural churn brought to you by VC funded marketing.

Im not interested in any system that require me to write a document begging an LLM to follow instructions, only to have it randomly ignore those instructions whenever its convenient.

[jswny]

This is just a formalization of an existing pattern many people were already using.

Putting a list of short blurbs pointing Claude Code at a set of extra, longer sets of CLAUDE.md style information was being used to prevent auto loading that context until it was needed.

Instead of assuming this is just change for the sake of change, it’s actually a nice way to support a usage pattern that many of us found works well already

[throw-10-13]

If by "works well already" you mean "inconsistent prompt hacks that you have to constantly reinforce" then sure.

CLAUDE.md holds about as much weight has the "Classroom Rules" craft posters hanging in most kindergarten classrooms.

[jswny]

Then you have misplaced your complaints. It sounds like you just don’t like the general instruction following patterns of Claude. Which is fine, but that is nothing specific to this Skills feature