Skill

ralph

PRD-loop persistence mode: iterate BUILD until verifier passes or max blocked attempts. Triggers ralph keep going keywords and /ohc-ralph. Deactivate via stop ralph.

npx claudepluginhub iadr-dev/colab --plugin oh-my-colab

Tool Access

This skill is limited to using the following tools:

Read Write Bash

Preview

Operate with **`scripts/ralph.js`** and session state files.

SKILL.md

Similar Skills

using-superpowers

178.4k

Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.

3 files

superpowers

Stats

Stars1

Forks0

Last CommitMay 2, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Ralph persistence

Operate with scripts/ralph.js and session state files.

Lifecycle

Activate via keyword "ralph", "keep going", or /ohc-ralph. On first run without an active PRD, the script initializes .ohc/state/sessions/<id>/prd.json from the current task narrative.

Loop — execute BUILD iteration; verifier runs tests; persist RESULT-style narrative in worker notes where applicable.

Advance — on success mark story done and move to next prd.stories[] entry; on repeated block update attempt_count; hard-stop after stopOnBlocked (keyword-map default 3).

Deactivate — user says "stop ralph" or "ralph stop" (clears active skill flag in .ohc/state/active-skills.json).

State files

.ohc/state/ralph-state.json — active session id, story index, iteration counters

.ohc/state/sessions/<id>/prd.json — { goal, stories:[{title,status,attempt_count}], ... } per scripts/ralph.js

Guardrails

Do not claim DONE without verifier-aligned evidence.

If stories are ambiguous, widen them only after syncing with writing-plans or user OK.

Ralph persistence

Operate with scripts/ralph.js and session state files.

Lifecycle

Activate via keyword "ralph", "keep going", or /ohc-ralph. On first run without an active PRD, the script initializes .ohc/state/sessions/<id>/prd.json from the current task narrative.
Loop — execute BUILD iteration; verifier runs tests; persist RESULT-style narrative in worker notes where applicable.
Advance — on success mark story done and move to next prd.stories[] entry; on repeated block update attempt_count; hard-stop after stopOnBlocked (keyword-map default 3).
Deactivate — user says "stop ralph" or "ralph stop" (clears active skill flag in .ohc/state/active-skills.json).

State files

.ohc/state/ralph-state.json — active session id, story index, iteration counters
.ohc/state/sessions/<id>/prd.json — { goal, stories:[{title,status,attempt_count}], ... } per scripts/ralph.js

Guardrails

Do not claim DONE without verifier-aligned evidence.
If stories are ambiguous, widen them only after syncing with writing-plans or user OK.