wquguru Ralph Agent
Autonomous coding agent that implements user stories iteratively.
Routing
Based on user intent, load the corresponding instruction file:
| Intent | Keywords | Action |
|---|---|---|
| PRD | prd, create, generate, plan | Read {baseDir}/prd.md |
| Prep | prep, prepare, convert, setup | Read {baseDir}/prep.md |
| Run | run, execute, go, start | Read {baseDir}/run.md |
Shared Configuration
| Item | Path |
|---|---|
| Working directory | .claude/ralph-ryan/ |
| PRD markdown | .claude/ralph-ryan/prd.md |
| PRD JSON | .claude/ralph-ryan/prd.json |
| Progress log | .claude/ralph-ryan/progress.txt |
| Archived runs | .claude/ralph-ryan-archived/<date>-<featureName>/ |
Quick Reference
# Workflow
# Step1: manual
/ralph-ryan prd [describe your feature]
# Step2: manual
/ralph-ryan prep
# Step3: manual + auto
/ralph-loop:ralph-loop "Load skill ralph-ryan and execute run mode." --max-iterations 10 --completion-promise COMPLETE
IMPORTANT NOTE: there are two ralph-loop in the command /ralph-loop:ralph-loop, don't trim it.