agentleFS
Sign inStart free
iadr-deviadr-dev/colab/skills/ralph/SKILL.md

ralph

Skill2 starsChanged 7 months agoMITView on GitHub

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.

45 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ultrawork, cancel and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • zephyrpersonalSkill

    ultrawork

    Obsessive task completion mode (Sisyphus Mode) - activates maximum intensity work with todo continuation enforcement

    Also in 7 projects that use this

  • woosikkimSkill

    cancel

    Clear any stale OMC-Slim state

    Also in 7 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 5 projects that use this

  • Jurel89Skill

    ultraqa

    QA cycling loop — build/lint/test, fix, retry up to 5 cycles

    Also in 3 projects that use this

  • JokerRunSkill

    compound-engineering

    Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan → Work → Review → Compound loop where each unit of engineering makes subsequent work easier. Triggers on: plan this feature, implement this, review this code, compound learnings, create implementation plan, systematic development.

    Also in 3 projects that use this

  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 41 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not claim DONE without verifier-aligned evidence.

    line 27
  2. Very specific:

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

    line 28

“Common” is measured: kept by at least 6 in 10 of the 41 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ralph persistence

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

Lifecycle

  1. 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.
  2. Loop — execute BUILD iteration; verifier runs tests; persist RESULT-style narrative in worker notes where applicable.
  3. 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).
  4. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free