A self-referential persistence loop that won't quit until every user story in your PRD passes verification. It auto-generates a prd.json from your task, breaks work into discrete stories with testable acceptance criteria, then iterates until each one is verified complete by a reviewer (architect, critic, or codex). Sessions persist across retries, long operations run in background, and you get structured progress tracking. The mandatory reviewer step prevents the usual "looks good enough" problem where implementations get marked done with half the edge cases skipped. Skip this if you want manual control or just need a quick fix. Reach for it when "finish this completely" actually means completely.

skills.sh installs
1K
GitHub stars
40.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add yeachan-heo/oh-my-claudecode --skill ralph --agent claude-code

Installs into .claude/skills of the current project.

Files

[RALPH - ITERATION {{ITERATION}}/{{MAX}}]

Your previous attempt did not output the completion promise. Continue working on the task.

Ralph is a PRD-driven persistence loop that keeps working on a task until ALL user stories in prd.json have passes: true and are reviewer-verified. It combines session persistence, automatic retry on failure, structured story tracking, and mandatory verification before completion. NON-NEGOTIABLE, runs before any story work and at every verification gate:

Sponsors

Details

Repository
github.com/yeachan-heo/oh-my-claudecode
First seen
Jun 3, 2026

More from yeachan-heo/oh-my-claudecode

All 37

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs