[flagged]
AGENTS.md outperforms skills in our agent evals
31–40 of 212 posts
Re: AGENTS.md outperforms skills in our agent evals
#32Ah nice… vercel is vibecoded
Re: AGENTS.md outperforms skills in our agent evals
#33Wouldn't this have been more readable with a \n newline instead of a pipe operator as a seperator? This wouldn't have made the prompt longer.
Re: AGENTS.md outperforms skills in our agent evals
#34Am I missing something here? Obviously directly including context in something like a system prompt will put it in context 100% of the time. You could just as easily take all of an agent's skills, feed it to the agent (in a system prompt, or similar) and it will follow the instructions more reliably. However, at a certain point you have to use skills, because including it in the context every time is wasteful, or not…
> Obviously directly including context in something like a system prompt will put it in context 100% of the time.
How do you suppose skills get announced to the model? It's all in the context in some way. The interesting part here is: Just (relatively naively) compressing stuff in the AGENTS.md seems to work better than however skills are implemented.
Re: AGENTS.md outperforms skills in our agent evals
#35Title is: AGENTS.md outperforms skills in our agent evals
Re: AGENTS.md outperforms skills in our agent evals
#36[flagged]
Why could you not have a combination of both?
Re: AGENTS.md outperforms skills in our agent evals
#37you are telling me that a markdown saying:
*You are the Super Duper Database Master Administrator of the Galaxy*
does not improve the model ability reason about databases?
Re: AGENTS.md outperforms skills in our agent evals
#38This largely mirrors my experience building my custom agent
1. Start from the Claude Code extracted instructions, they have many things like this in there. Their knowledge share in docs and blog on this aspect are bar none
2. Use AGENTS.md as a table of contents and sparknotes, put them everywhere, load them automatically
3. Have topical markdown files / skills
4. Make great tools, this is still opaque in my mind to explain, lots of overlap with MCP and skills, conceptually they are the same to me
5. Iterate, experiment, do weird things, and have fun!
I changed read/write_file to put contents in the state and presented in the system prompt, same for the agents.md, now working on evals to show how much better this is, because anecdotally, it kicks ass
Re: AGENTS.md outperforms skills in our agent evals
#39Ah nice… vercel is vibecoded
web people opted into react, dude. that says a lot.
they used prisma to handle their database interactions. they preached tRPC and screamed TYPE SAFETY!!!
you really think these guys will ever again touch the keyboard to program? they despise programming.
Re: AGENTS.md outperforms skills in our agent evals
#40Am I missing something here? Obviously directly including context in something like a system prompt will put it in context 100% of the time. You could just as easily take all of an agent's skills, feed it to the agent (in a system prompt, or similar) and it will follow the instructions more reliably. However, at a certain point you have to use skills, because including it in the context every time is wasteful, or not…
> Obviously directly including context in something like a system prompt will put it in context 100% of the time. How do you suppose skills get announced to the model? It's all in the context in some way. The interesting part here is: Just (relatively naively) compressing stuff in the AGENTS.md seems to work better than however skills are implemented.
Isn't the difference that a skill means you just have to add the script name and explanation to the context instead of the entire script plus the explanation?