> we recommend keeping task-specific instructions in separate markdown files with self-descriptive names somewhere in your project.
Why should we do this when anthropic specifically recommends creating multiple CLAUDE.md files in various directories where the information is specific and pertinent? It seems to me that anthropic has designed claude to look for claude.md for guidance, and randomly named markdown files may or may not stand out to it as it searches the directory.
You can place CLAUDE.md files in several locations:
> The root of your repo, or wherever you run claude from (the most common usage). Name it CLAUDE.md and check it into git so that you can share it across sessions and with your team (recommended), or name it CLAUDE.local.md and .gitignore it
Any parent of the directory where you run claude. This is most useful for monorepos, where you might run claude from root/foo, and have CLAUDE.md files in both root/CLAUDE.md and root/foo/CLAUDE.md. Both of these will be pulled into context automatically
Any child of the directory where you run claude. This is the inverse of the above, and in this case, Claude will pull in CLAUDE.md files on demand when you work with files in child directories
Your home folder (~/.claude/CLAUDE.md), which applies it to all your claude sessions
I wish they would at least include the japanese cc subtitles. They must already exist so I don't understand why they can't just be packaged along with the other subs.
I've only used LLMs with Elixir, so I don't have any other experience for comparison, but I've found that although Claude frequently employs the wrong approaches in Elixir, I usually know when he'll have trouble and just ask him to read pertinent documentation first. So long as he's read the manual he seems to do just fine.
Why should first-class concurrency needs be required to script in Elixir? This question seems to imply that Python is somehow a default language and special requirements must be needed to justify writing in something else. Elixir is general-use and pleasant to write scripts in so seems reasonable to me for someone to do so if that's their thing.
Why should we do this when anthropic specifically recommends creating multiple CLAUDE.md files in various directories where the information is specific and pertinent? It seems to me that anthropic has designed claude to look for claude.md for guidance, and randomly named markdown files may or may not stand out to it as it searches the directory.
You can place CLAUDE.md files in several locations:
> The root of your repo, or wherever you run claude from (the most common usage). Name it CLAUDE.md and check it into git so that you can share it across sessions and with your team (recommended), or name it CLAUDE.local.md and .gitignore it Any parent of the directory where you run claude. This is most useful for monorepos, where you might run claude from root/foo, and have CLAUDE.md files in both root/CLAUDE.md and root/foo/CLAUDE.md. Both of these will be pulled into context automatically Any child of the directory where you run claude. This is the inverse of the above, and in this case, Claude will pull in CLAUDE.md files on demand when you work with files in child directories Your home folder (~/.claude/CLAUDE.md), which applies it to all your claude sessions
https://www.anthropic.com/engineering/claude-code-best-pract...