Claude Skills are awesome, maybe a bigger deal than MCP

Post by 3abiton » Fri, Oct 17, 2025, 10:04 PM UTC

kasey_junk wrote: post #161

tptacek wrote: post #110

I do think the big story here is how hyperfocused and path-dependent people got on MCP, when the actually-interesting thing is simply "tool calls". Tool calls are incredibly interesting and useful. MCP is just one means to that end, and not one of the better ones.

MCP seems valuable in that it teaches the llm about oauth. So you can do server based tool calls. Before that you had to install each cli you wanted and it would invariably be doing some auth thing under the covers. Took calling was certainly the big llm advantage but “hey tools should probably auth correctly” is pretty valuable.

Post by bird0861 » Fri, Oct 17, 2025, 10:09 PM UTC

simonw wrote: post #139

roflcopter69 wrote: post #129

Earlier quoted context omitted.

I'd be really interested in what you mean. Are the any studies that quantify this difference in model performance when using JSON or XML? What could be a good intuition for why there might be a big difference? If XML is better than JSON for LLMs, why isn't everyone and the grandma recommending me to use XML instead of JSON? Why is Google Gemini API offering structured output only with JSON schema instead of XML schem…

I don't know if the XML is better than JSON thing still holds with this year's frontier models, but it was definitely a thing last year. Here's Anthropic's documentation about that: https://docs.claude.com/en/docs/build-with-claude/prompt-eng... Note that they don't actually suggest that the XML needs to be VALID! My guess was that JSON requires more characters to be escaped than XML-ish syntax does, plus matching op…

Post by greymalik » Fri, Oct 17, 2025, 10:13 PM UTC

simonw wrote: post #170

primer42 wrote: post #157

I've been able to build the equivalent of skills with a few markdown files. I need to remind my agent every so often to use a skill but usually once per session at most. I don't get what's so special about Claude doing this?

Part of it is that they gave a name to a useful pattern that people had already been discovering independently. Names are important, because they mean we can start having higher quality conversations about the pattern. Anthropic also realized that this pattern solves one of the persistent problems with coding agents: context pollution. You need to stuff as little material as possible into the context to enable the to…

Post by imiric » Fri, Oct 17, 2025, 10:15 PM UTC

koolala wrote: post #107

dist-epoch wrote: post #91

Earlier quoted context omitted.

Funny thing, pseudo-XML is going through a big resurgence right now, because models love it, while they seriously struggle with JSON.

HTML? Is the main advantage of XML for understandability the labeled closing tags? Lisp has the same struggle too?

Post by jhallenworld » Fri, Oct 17, 2025, 10:18 PM UTC

magicalhippo wrote: post #138

idk-92 wrote: post #108

Earlier quoted context omitted.

tbh wolfram alpha was the craziest thing ever. haven't done much research on how this was implemented back in the day but to achieve what they did for such complex mathematical problems without AI was kind of nuts

Would really like something selfhosted that does the basic Wolfram Alpha math things. Doesn't need the craziest math capability but standard symbolic math stuff like expression reduction, differentiation and integration of common equations, plotting, unit wrangling. All with an easy to use text interface that doesn't require learning.