Automated summary
Starts an autonomous development loop that executes PRD user stories with smart failure handling, skill-based verification, and checkpointing.
Strengths
- Fully autonomous execution without human oversight after launch
- Robust failure management with circuit breaker and error injection
- Post-step verification using security and performance skills
- Resumable from checkpoint in case of interruption
Limitations
- Requires a pre-defined and structured PRD plan
- Security modes may restrict necessary actions
- May be inefficient for very complex projects without customization
Use this skill when you have a clear PRD plan and want to execute it autonomously with monitoring and resume capability.
Do not use it if the PRD plan is poorly defined, if continuous human supervision is needed, or if required actions exceed the permissions of the chosen security mode.
Security analysis
CautionThe skill orchestrates an autonomous development loop using Bash and code modification tools. While it includes safety measures like circuit breakers and security modes, the inherent power and autonomy pose significant risk if misused or if the PRD contains malicious instructions. Not explicitly destructive, but requires caution.
- •Uses Bash and Write/Edit tools autonomously, which could lead to destructive actions if not properly constrained.
- •Supports 'yolo' security mode that grants full permissions, increasing risk of unintended damage.
- •Autonomous loop may execute arbitrary code based on PRD stories, potentially leading to security breaches.
Examples
/ralph-ultra:ralph-run/ralph-ultra:ralph-run --max-iterations 5 --security sandbox/ralph-ultra:ralph-run --resumename: ralph-run description: Start the Ralph Ultra autonomous development loop. Iterates through PRD stories with smart failure handling, skill-based verification, and checkpointing. Use when ready to execute a PRD plan autonomously. allowed-tools: Read, Write, Edit, Bash, Grep, Glob
Ralph Ultra Autonomous Loop
Start the smart adaptive development loop that iterates through PRD stories.
What this does
- Pre-flight checks — Runs environment-doctor and deep-codebase-navigator
- Story selection — Picks next story respecting dependencies and failure history
- Prompt construction — Builds context from CLAUDE.md, skills, progress, and error history
- Execution — Invokes Claude/AMP with appropriate security flags
- Verification — Runs post-iteration skills (security-auditor, performance-guardian)
- Failure handling — Circuit breaker at 3 failures, error injection for self-correction
- Checkpointing — Saves state after each iteration for resumability
Usage
/ralph-ultra:ralph-run [--max-iterations N] [--security sandbox|standard|yolo] [--tool claude|amp] [--resume]
Options
| Option | Default | Description |
|--------|---------|-------------|
| --max-iterations | 10 | Maximum loop iterations |
| --security | standard | Security mode (sandbox/standard/yolo) |
| --tool | claude | AI tool to use |
| --resume | false | Resume from last checkpoint |
Loop Flow
Pre-flight Skills → Pick Story → Build Prompt → Execute →
↓ Success: Mark done, run post-iteration skills → Next story
↓ Failure: Record error, inject context → Retry (max 3) → Block story
Security Modes
- sandbox: Read-only analysis, no file modifications
- standard: Allowlist-based, only permitted commands
- yolo: Full permissions (requires explicit confirmation)
Monitoring
While the loop runs:
- View live dashboard:
/ralph-ultra:ralph-dashboard - Check status:
/ralph-ultra:ralph-status - Session logs:
.ralph-ultra/sessions/current/log.jsonl
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ralph-ultra-autonomous-loop-mm8o51oh/download' --output '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md.part' && mv '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md.part' '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Write, Edit, Bash, Grep, Glob
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md' && test -s '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ralph-run' && cp -R '.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh' '.claude/skills/ralph-run'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh'openskills read 'ralph-ultra-autonomous-loop-mm8o51oh'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/ralph-ultra-autonomous-loop-mm8o51oh/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.