Claude will load the name and description of each enabled skill into context at startup[0]; the LLM needs to know what it can invoke, after all. It's negligible for a few skills, but a hundred skills will likely have some impact, e.g. deemphasizing other skills by adding noise.
You could be thinking of the Claude tool search tool [0][1], which lets it do that on-demand loading. Skills (like another comment mentioned) have a progressive disclosure mechanism built-in. Agent Skills [2] appear to be the common format across most of the tools, but I have no idea if this actually has tool provider buy-in.
> gws ships 100+ SKILL.md files
Which must altogether be hundreds of lines of YAML frontmatter polluting your context.