Completely agree with both points. Skills replacing one-off microservices and agents writing their own skills feel like two sides of the same coin to me.
I’m a solo developer building a markdown-first slide editing app. The core format is just Markdown with --- slide separators, but it has custom HTML comment directives for layouts (<!-- layout: title -->, <!-- layout: split -->, etc.) and content-type detection for tables, code blocks, and Mermaid diagrams. It’s a small DSL, but enough that an LLM without context will generate slides that don’t render optimally.
Right now my app is designed for copy-paste from external LLMs, which means users have to manually include the format spec in their prompts every time. But your comment about agents writing skills made me realize the better path: I could just ask Claude Code to read my parser and layout components, then generate a Slide_Syntax_Guide skill for me. The agent already understands the codebase—it can write the definitive spec better than I could document it manually.
I think this framework explains why the best presentations aren't the ones packed with the most information. Like a slide full of bullet points feels kind of like a frictionless wall to me - there's nothing for the audience to grab onto. But a slide with one provocative question, or a single surprising statistic, is covered in doorknobs. It gives people something to mentally reach for.
The flip side: slides designed by committee oftem tend to remove all the doorknobs. Every bold claim seems to gets softened, every interesting aside gets cut for time, etc., until you're left with something that nobody can disagree with but nobody finds very interesting either.
