Specification-first AI development powered by Ouroboros. An agent skill from aiskillstore/marketplace.

No licenceAuto-check: notesAgent Workflows

Install Ralph

skills CLI
$ npx skills add aiskillstore/marketplace --skill ralph -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiskillstore/marketplace ralph --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiskillstore/marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/supercent-io/ralph .claude/skills/ralph && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ralph
GitHub stars
430
Used in
1 other repo
Token cost
~4.2k tokens
SKILL.md length
962 words
Files
4 (incl. scripts)
Skills in repo
1,108
Repo updated
First seen
Licence
None found

At a glance

Specification-first AI development powered by Ouroboros. An agent skill from aiskillstore/marketplace.

  • Works in 10 steps: Commands (Full Reference) → Interview → Specification Flow → Ralph — Persistent Loop Until Verified → …
  • User says ralph
  • SKILL.md covers When to use this skill, Core Architecture: The Loop, 1. Commands (Full Reference) and 2. Interview → Specification…, plus 6 more sections
  • Runs Shell scripts from its folder; calls claude, gemini and bash; reaches github.com

What it does

Ralph is an agent skill from aiskillstore/marketplace. Specification-first AI development powered by Ouroboros. Socratic questioning exposes hidden assumptions before writing code. Evolutionary loop (Interview → Seed → Execute → Evaluate → Evolve) runs until ontology converges. Ralph mode persists until verification passes — the boulder never stops. Use when user says "ralph", "ooo", "don't stop", "must complete", "until it works", "keep going", "interview me", or "stop prompting".

Its SKILL.md is about 4.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/setup-codex-hook.sh` and `skill-report.json`).

It sits in Agent Workflows, covering Tutoring and explanations and Requirements gathering. The repository describes itself as: Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

When your agent uses it

  • User says ralph
  • Tasks that involve Tutoring and explanations
  • Tasks that involve Requirements gathering

Example prompts

  • “t stop”
  • “must complete”
  • “until it works”
  • “/ralph”

Requirements

  • Python 3
  • A Bash shell
  • Pre-approved tools (allowed-tools): Read, Write, Bash, Grep, Glob, WebFetch

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Commands (Full Reference)
  2. Interview → Specification Flow
  3. Ralph — Persistent Loop Until Verified
  4. Evolutionary Loop (Evolve)
  5. The Nine Minds (Agents)
  6. Unstuck — Lateral Thinking
  7. Platform Installation & Usage
  8. Platform Support Matrix
  9. Quick Reference
  10. Installation

What it can do on your machine

Read from SKILL.md and the folder at commit ad8daf7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash
    • Grep
    • Glob
    • WebFetch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • claude
    • gemini
    • bash
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ralph loads about 4.2k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 962 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash, Grep, Glob, WebFetch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 962 words (~4,190 tokens).

“Each cycle evolves, not repeats. Evaluation output feeds back as input for the next generation until the system converges.”

— opening of SKILL.md by aiskillstore
name
ralph
allowed-tools
Read, Write, Bash, Grep, Glob, WebFetch
metadata.tags
ralph, ouroboros, specification-first, socratic, interview, seed, evaluate, evolve, loop, completion, self-referential, multi-platform, claude, codex, gemini…
metadata.platforms
Claude Code, Codex, Gemini-CLI, OpenCode
metadata.keyword
ralph
metadata.version
3.0.0
metadata.source
Q00/ouroboros

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts) in skills/supercent-io/ralph of aiskillstore/marketplace.

  • SKILL.md
  • SKILL.toon
  • scripts/setup-codex-hook.sh
  • skill-report.json

Open the folder on GitHubat commit ad8daf7

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aiskillstore/marketplace, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Ralph next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ralph compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ralph this skillaiskillstore/marketplace4301 repos~4.2kAutomated safety check: NotesNone
Deep Interviewzereight/gitlab-mcp2k1 repos~725Automated safety check: PassMIT
Hoyeon Discussteam-attention/hoyeon173—~458Automated safety check: PassMIT
Deep Divebyungjunjang/jangpm-meta-skills121—~2.7kAutomated safety check: PassNone
Deep Divebyungjunjang/jangpm-meta-skills121—~2.5kAutomated safety check: PassNone
Grill Mesoftspark/ai-toolkit179—~732Automated safety check: NotesApache-2.0

Similar skills

  • Deep Interview

    zereight/gitlab-mcp

    Socratic deep interview with mathematical ambiguity gating. An agent skill from zereight/gitlab-mcp.

    2k GitHub starsUsed in 1 repo~725 tokens
    Agent WorkflowsAuto-check passed
  • Hoyeon Discuss

    team-attention/hoyeon

    Hoyeon Socratic discussion workflow for Codex. An agent skill from team-attention/hoyeon.

    173 GitHub stars~458 tokensUpdated 4 mo ago
    Agent WorkflowsAuto-check passed
  • Deep Dive

    byungjunjang/jangpm-meta-skills

    A Codex skill for Socratic interviews that deepen a spec or refine an existing agent blueprint.

    121 GitHub stars~2.7k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Deep Dive

    byungjunjang/jangpm-meta-skills

    Socratic interview skill to deepen a spec or refine an existing agent blueprint.

    121 GitHub stars~2.5k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Grill Me

    softspark/ai-toolkit

    Stress-tests a plan via Socratic questioning down each decision branch.

    179 GitHub stars~732 tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes
  • Gsd Explore

    open-gsd/gsd-core

    Socratic ideation and idea routing — think through ideas before committing to plans

    10k GitHub starsUsed in 2 repos~176 tokens
    Agent WorkflowsAuto-check: notes

More from aiskillstore/marketplace

All 1,108 skills in this repo
  • Code Stats

    aiskillstore/marketplace

    Analyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs).

    430 GitHub starsUsed in 2 repos~697 tokens
    Auto-check: notes
  • File Search

    aiskillstore/marketplace

    Modern file and content search using fd, ripgrep (rg), and fzf.

    430 GitHub starsUsed in 2 repos~598 tokens
    Auto-check: notes
  • Data Processing

    aiskillstore/marketplace

    Process JSON with jq and YAML/TOML with yq. An agent skill from aiskillstore/marketplace.

    430 GitHub starsUsed in 1 repo~720 tokens
    Auto-check: notes
  • Doc Scanner

    aiskillstore/marketplace

    Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance.

    430 GitHub starsUsed in 1 repo~644 tokens
    Auto-check: notes
  • Find Replace

    aiskillstore/marketplace

    Modern find-and-replace using sd (simpler than sed) and batch replacement patterns.

    430 GitHub starsUsed in 1 repo~527 tokens
    Auto-check: notes
  • Investigating Codebases

    aiskillstore/marketplace

    Automatically activated when user asks how something works, wants to understand unfamiliar code, needs to explore a new codebase, or asks questions like "where is X implemented?", "how does Y…

    430 GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check: notes

Questions about Ralph

What does Ralph do?

Specification-first AI development powered by Ouroboros. An agent skill from aiskillstore/marketplace. Ralph is an agent skill from aiskillstore/marketplace. Specification-first AI development powered by Ouroboros.

When should I use Ralph?

Ralph fits situations like: user says ralph; tasks that involve Tutoring and explanations; tasks that involve Requirements gathering.

How do I install Ralph in Claude Code?

Run `npx skills add aiskillstore/marketplace --skill ralph -a claude-code`. Or copy the skill folder (skills/supercent-io/ralph in aiskillstore/marketplace) into .claude/skills/ralph in your project. Claude Code loads it when a task matches its description.

How do I install Ralph in Codex?

Run `npx skills add aiskillstore/marketplace --skill ralph -a codex`. Or copy the skill folder (skills/supercent-io/ralph in aiskillstore/marketplace) into .agents/skills/ralph in your project. Codex loads it when a task matches its description.

Can I use Ralph in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiskillstore/marketplace --skill ralph -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph, .gemini/skills/ralph, .github/skills/ralph and .opencode/skills/ralph in your project.

What does Ralph need to run?

Going by SKILL.md and its folder, Ralph needs a shell for the scripts in its folder and the command-line tools its instructions call (claude, gemini, bash and npx). Our summary lists: Python 3; A Bash shell. Its frontmatter pre-approves these tools: Read, Write, Bash, Grep, Glob, WebFetch.

Does Ralph access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Ralph safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ralph use?

No licence was found for Ralph or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Ralph use?

About 4.2k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ralph?

Skills that share tags, products or a category with Ralph: Deep Interview (zereight/gitlab-mcp, 2k stars), Hoyeon Discuss (team-attention/hoyeon, 173 stars), Deep Dive (byungjunjang/jangpm-meta-skills, 121 stars) and Deep Dive (byungjunjang/jangpm-meta-skills, 121 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ralph?

aiskillstore (a GitHub organization) maintains it in aiskillstore/marketplace, which has 430 GitHub stars. The repository holds 1,108 skills in this directory. The repository was last updated on October 7, 2026.

Source: aiskillstore/marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.