Viewing profile — alex_metacraft

So cool! I gave it a try and used it for web design and presentations. It satisfied both of my needs and I gave up on the Pencil MCP immediately.

[flagged]

[dead]

Good catch on the numbers. 29/33 vs 33/33 is the kind of gap that could easily be noise with that sample size. You'd need hundreds of runs to draw any meaningful conclusion about a…

Hey HN. I've been working on askill, a CLI package manager for agent skills (SKILL.md files used by Claude Code, Codex, Cursor, etc.). There are already several skill directories a…

I think this experiment has a fundamental flaw in its comparison setup. What they're comparing is: (A) a skill with a short description in the frontmatter, which the agent may or m…

This is a really interesting finding. It makes sense when you think about what the training data looks like — first person statements in a system prompt pattern-match to "internal …