Self-referential completion loop for AI CLI tools. Re-runs the agent on the same task across turns with fresh context each iteration, until the completion promise is detected or max iterations is reached.
Quickly install ralph AI skill to your development environment via command line
Source: supercent-io/skills-template.
The loop happens across agent turns, controlled by an AfterAgent hook.
Provide a verifiable definition of "done." The --completion-promise is crucial.
Always use --max-iterations as a safety net to prevent infinite loops.
Self-referential completion loop for AI CLI tools. Re-runs the agent on the same task across turns with fresh context each iteration, until the completion promise is detected or max iterations is reached. Source: supercent-io/skills-template.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/supercent-io/skills-template --skill ralphSelf-referential completion loop for AI CLI tools. Re-runs the agent on the same task across turns with fresh context each iteration, until the completion promise is detected or max iterations is reached. Source: supercent-io/skills-template.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/supercent-io/skills-template --skill ralph Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/supercent-io/skills-template