Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Rudel – Claude Code Session Analytics

github.com

Post reply on HN
Print view View original

81–90 of 108 posts

Re: Show HN: Rudel – Claude Code Session Analytics

#81

Post by conception »

dmix wrote: post #50

I've seen Claude ignore important parts of skills/agent files multiple times. I was running a clean up SKILL.md on a hundred markdown files, manually in small groups of 5, and about half the time it listened and ran the skill as written. The other half it would start trying to understand the codebase looking for markdown stuff for 2min, for no good reason, before reverting back to what the skill said. LLMs are far fr…

https://scottspence.com/posts/measuring-claude-code-skill-ac...

This works in my experience

Re: Show HN: Rudel – Claude Code Session Analytics

#86

Post by evrendom »

smallerfish wrote: post #85

> content, the content or transcript of the agent session Does this include the files being worked on by the agent in the session, or just the chat transcript?

file content is also be uploaded as well https://github.com/obsessiondb/rudel?tab=readme-ov-file#secu...

if you dont trust us with that data though (which i can understand) you can host that thing locally on your machine

Re: Show HN: Rudel – Claude Code Session Analytics

#88

Post by evrendom »

tmaly wrote: post #87

I have seen numbers claiming tools are only called 59% of the time. Saw another comment on a different platform where someone floated the idea of dynamically injecting context with hooks in the workflow to make things more deterministic.

interesting, where did you see that?

Re: Show HN: Rudel – Claude Code Session Analytics

#89

Post by stpedgwdgfhgdd »

dmix wrote: post #50

I've seen Claude ignore important parts of skills/agent files multiple times. I was running a clean up SKILL.md on a hundred markdown files, manually in small groups of 5, and about half the time it listened and ran the skill as written. The other half it would start trying to understand the codebase looking for markdown stuff for 2min, for no good reason, before reverting back to what the skill said. LLMs are far fr…

Try the latest skill-creator, has a/b testing
Post reply on HN