from Hacker News

Show HN: AutoLearn Skills for self-improving agents

by toobulkeh on 10/22/25, 2:54 AM with 11 comments

• by toobulkeh on 10/22/25, 2:57 AM

  I vibe coded this at a hackathon a few weeks ago. The solution isn’t stable yet, but it’s similar to Claude Skills with the benefit of only needing an MCP client.

  I open sourced it too.

  It has a bit to go—like automatically monitoring reasoning traces and security—but I thought this would be easier to use than trying to maintain your own skills.md collection if the server handled more of it for you.

  I’d be curious if anyone thinks I should keep working on it. I’d love someone to collaborate with on it!

• by stpedgwdgfhgdd on 10/22/25, 6:34 AM

  I sometimes have to decide between running Claude Code headless with a prompt or let CC generate an application based on the prompt. (coining: Codification Threshold tradeoff)

  The tradeoff is that the prompt is non-deterministic, but also more flexible. It can handle unknown situations. The generated code executes much faster and reliable for known situations.

  If auto-learn would reduce the non-deterministic nature, i.e. chance of failing, that would speed up software development.

• by snowfield on 10/22/25, 8:58 AM

  This is a very interesting concept. I have a few questions though.

  Even if the agent has mcp tools avaible, you can't guarantee that it would necessarily use them right? I imagine that you'd have a lot of new tools that do nearly the same things.

  Also how does this scale? If the agent has like 300 tools.

• by drdeca on 10/22/25, 5:18 AM

  How does it determine whether the code it has for the skill, failed? (In order to determine that it needs to improve the code for that skill, I mean)

• by personjerry on 10/22/25, 5:04 AM

  I don't understand, it'd be nice to see even a single example of the application