Master orchestrator for generating Ralph Wiggum-compatible prompts. Analyzes task requirements and routes to appropriate generator (single-task, multi-task, project, or research). Use when you need to create any Ralph loop prompt and want automatic selection of the right generator.
/plugin marketplace add adaptationio/Skrillz/plugin install skrillz@skrillzThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Master skill for generating prompts optimized for the Ralph Wiggum autonomous loop technique. This orchestrator analyzes your task description and routes to the appropriate specialized generator:
| Task Type | Generator | Best For |
|---|---|---|
| Single focused task | ralph-prompt-single-task | Bug fixes, single features, refactoring |
| Multiple related tasks | ralph-prompt-multi-task | CRUD, multi-step features, migrations |
| Complete project | ralph-prompt-project | Greenfield apps, libraries, tools |
| Research/Analysis | ralph-prompt-research | Audits, planning, investigations |
Generate any Ralph prompt:
Use ralph-prompt-builder to create a prompt for: [describe your task]
Example:
Use ralph-prompt-builder to create a prompt for: Implementing user authentication with JWT for our Express API
The skill will:
| Indicators | Classification | Generator |
|---|---|---|
| Fix, repair, single change, one module | Single Task | ralph-prompt-single-task |
| Multiple features, CRUD, several endpoints | Multi-Task | ralph-prompt-multi-task |
| Build from scratch, new app, create tool | Project | ralph-prompt-project |
| Analyze, audit, compare, plan, investigate | Research | ralph-prompt-research |
To classify your task, consider:
Is this creating something new from scratch or modifying existing code?
How many distinct deliverables?
Does it involve investigation before action?
What's the completion criteria?
Provide a description including:
Template:
Task: [What you want to accomplish]
Context: [Relevant background - tech stack, existing code, etc.]
Requirements: [Specific requirements or constraints]
Outcome: [What success looks like]
The orchestrator will classify your task and explain why:
CLASSIFICATION: [Task Type]
REASONING: [Why this classification]
GENERATOR: ralph-prompt-[type]
Does this classification look correct? If not, specify your preferred type.
Each generator requires specific inputs:
Single Task:
Multi-Task:
Project:
Research:
The appropriate generator creates the prompt. Review and customize:
/ralph-wiggum:ralph-loop "[generated prompt]" --completion-promise "[YOUR_PROMISE]" --max-iterations [recommended]
Purpose: Focused tasks with clear success criteria
Structure:
Best practices:
Recommended iterations: 15-35
Purpose: Multiple related tasks organized in phases
Structure:
Best practices:
Recommended iterations: 35-100
Purpose: Complete projects from scratch
Structure:
Best practices:
Recommended iterations: 60-200
Purpose: Analysis, audits, planning, investigations
Structure:
Best practices:
Recommended iterations: 30-100
Good promises are:
Examples:
| Task Type | Good Promise | Why |
|---|---|---|
| Bug fix | AUTH_FIX_COMPLETE | Specific to what was fixed |
| CRUD | PRODUCT_CRUD_DONE | Names the resource |
| Project | TODO_API_V1_COMPLETE | Identifies the project |
| Research | SECURITY_AUDIT_DELIVERED | References deliverable |
The Ralph Wiggum technique is built on a key insight: failures are deterministic and fixable.
This means: Don't fear failures. They're expected and correctable. The loop will iterate until success.
Base recommendations by complexity:
| Complexity | Single Task | Multi-Task | Project | Research |
|---|---|---|---|---|
| Simple | 15 | 35 | 60 | 30 |
| Medium | 25 | 50 | 100 | 50 |
| Complex | 35 | 70 | 150 | 80 |
| Very Complex | - | 100 | 200 | 100 |
Adjust based on:
If task feels too large, consider splitting:
Project → Multiple Projects:
Instead of: "Build complete e-commerce platform"
Split into:
1. Project: User authentication service
2. Project: Product catalog API
3. Project: Shopping cart service
4. Project: Order processing service
Multi-Task → Separate Multi-Tasks:
Instead of: "Build full admin dashboard"
Split into:
1. Multi-Task: User management (CRUD + roles)
2. Multi-Task: Analytics dashboard
3. Multi-Task: Settings panel
Symptoms: Hitting max iterations without completion
Causes and fixes:
Fix: Specify the generator explicitly:
Use ralph-prompt-single-task (not multi-task) for: [task]
Fix: Ensure your input includes:
After generating a prompt:
# Copy the generated prompt to a file or use directly
/ralph-wiggum:ralph-loop "[YOUR_GENERATED_PROMPT]" \
--completion-promise "YOUR_PROMISE" \
--max-iterations 50
# Monitor progress
head -10 .claude/ralph-loop.local.md
# Cancel if needed
/ralph-wiggum:cancel-ralph
Is this research/analysis/planning?
├─ YES → ralph-prompt-research
└─ NO → Is this building a complete app from scratch?
├─ YES → ralph-prompt-project
└─ NO → Are there multiple related deliverables?
├─ YES → ralph-prompt-multi-task
└─ NO → ralph-prompt-single-task
Before generating, have ready:
Before running the prompt:
Specialized Generators:
ralph-prompt-single-task - Single focused implementationsralph-prompt-multi-task - Multiple related tasksralph-prompt-project - Complete projectsralph-prompt-research - Analysis and planningRalph Loop Commands:
/ralph-wiggum:ralph-loop - Start a loop/ralph-wiggum:cancel-ralph - Cancel active loop/ralph-wiggum:help - Get helpActivates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.