← Back to context Comment by wouldbecouldbe 15 hours ago It seems to mostly ignore Claude.md 3 comments wouldbecouldbe Reply csar 12 hours ago It’s told to only use it if relevant because most people write bad ones. Someone should write a tool to assess CLAUDE.md quality. songodongo 14 hours ago If you can test how often it is being used by having a line in there saying something like “You must start every non-code response with ‘Woohoo!’” AndyNemmity 15 hours ago It does, Claude.md is the least effective way to communicate to it.It's always interesting reading other people's approaches, because I just find them all so very different than my experience.I need Agents, and Skills to perform well.
csar 12 hours ago It’s told to only use it if relevant because most people write bad ones. Someone should write a tool to assess CLAUDE.md quality.
songodongo 14 hours ago If you can test how often it is being used by having a line in there saying something like “You must start every non-code response with ‘Woohoo!’”
AndyNemmity 15 hours ago It does, Claude.md is the least effective way to communicate to it.It's always interesting reading other people's approaches, because I just find them all so very different than my experience.I need Agents, and Skills to perform well.
It’s told to only use it if relevant because most people write bad ones. Someone should write a tool to assess CLAUDE.md quality.
If you can test how often it is being used by having a line in there saying something like “You must start every non-code response with ‘Woohoo!’”
It does, Claude.md is the least effective way to communicate to it.
It's always interesting reading other people's approaches, because I just find them all so very different than my experience.
I need Agents, and Skills to perform well.