Command
coderabbit-review
Handle CodeRabbit AI review cycles after creating a PR
Development
Command
/work-until
Start a work-until loop that keeps you working on a task until completion
Install
$ npx -y skills add markmdev/meridian --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/work-until
Context preview
What this command does when you run it.
Start a work-until loop that keeps you working on a task until completion
Command definition
work-until.mddescription: Start a work-until loop that keeps you working on a task until completion argument-hint: TASK [--completion-phrase "TEXT"] [--max-iterations N] allowed-tools: Bash
Work-Until Loop
!`[ -f .meridian/scripts/setup-work-until.sh ] || { echo "Error: Run /work-until from project root directory" >&2; exit 1; }; .meridian/scripts/setup-work-until.sh $ARGUMENTS`
!`cat .meridian/prompts/work-until-loop.md`
Ships withmeridian
Meridian makes Claude Code more reliable on real projects. It adds persistent project context, smarter session handoff, and lightweight workflow enforcement so Claude is less likely to lose the plot halfway through a long task.
Get the whole plugin