Instead of including all these instructions in CLAUDE.md, have you considered using custom Skills? I’ve implemented something similar, and Skills works really well. The only downside is that it may consume more tokens.

▲

stpedgwdgfhgdd 14 hours ago | parent | next [-]

The matching logic for a skill is pretty strict. I wonder whether mentioning ‘git’ in the front matter and using ‘gitlab’ would give a match for a skill to get triggered.

▲

taytus 14 hours ago | parent | prev [-]

Yes, sometimes skills are more reliable, but not always. That is the biggest culprit to me so far. The fact that you cannot reliably trust these LLMs to follow steps or instructions makes them unsuitable for my applications.

	▲	notpublic 14 hours ago \| parent [-]
		Another thing that helps is adding a session hook that triggers on startup\|resume\|clear\|compact to remind Claude about your custom skills. Keeps things consistent, especially when you're using it for a long time without clearing context