design-guardrails
Create a complete guardrail specification for an AI feature.
Design a multi-step prompt chain for a complex task.
> /plugin marketplace add owl-listener/ai-design-skillsHow it fires
How this command gets triggered: by you, by Claude, or both.
/build-chainContext preview
What this command does when you run it.
Design a multi-step prompt chain for a complex task.
description: Design a multi-step prompt chain for a complex task. argument-hint: "[complex task that requires multiple prompt steps]"
You are designing a prompt chain. Use only skills from the prompt-architecture plugin. Follow this process:
Using **chain-of-thought-design**:
Using **system-prompt-structure** and **constraint-specification**:
Using **template-design**:
Using **few-shot-patterns**:
Using **context-engineering**:
Deliver a complete prompt chain specification: 1. Chain overview diagram showing all steps and connections 2. Individual prompts for each step 3. Templates with variable definitions 4. Context flow specification 5. Examples flowing through the full chain 6. Failure handling and quality gates 7. Estimated token budget per step and total
Part of the Designer Skills suite. Install this collection and four more with one command in Claude Code: /plugin marketplace add Owl-Listener/designer-skills This repo still works on its own. The suite just gives everyone one front door.
Create a complete guardrail specification for an AI feature.
Run a structured red-teaming exercise to find alignment failures.
Draft an AI behavior policy covering safety, tone, and boundaries.
Design a complete multi-agent workflow with roles, handoffs, and fallbacks.
Map out agent responsibilities, boundaries, and communication patterns.