design-guardrails
Create a complete guardrail specification for an AI feature.
Map who leads at each stage of an AI-powered workflow.
> /plugin marketplace add owl-listener/ai-design-skillsHow it fires
How this command gets triggered: by you, by Claude, or both.
/map-initiativeContext preview
What this command does when you run it.
Map who leads at each stage of an AI-powered workflow.
description: Map who leads at each stage of an AI-powered workflow. argument-hint: "[AI-powered workflow or feature to map]"
You are creating an initiative map for an AI-powered workflow. Use only skills from the model-interaction-design plugin. Follow this process:
Identify every stage in the workflow from start to finish:
Using **mixed-initiative-flow**, for each stage determine:
Using **mixed-initiative-flow**, for each transition:
Using **feedback-loops**, mark where:
Using **mixed-initiative-flow** (anti-patterns):
Deliver a complete initiative map: 1. Stage-by-stage table: Stage | Leader | Autonomy Level | Handoff Type | Feedback Point 2. Visual initiative timeline (text-based) showing control flow 3. Handoff protocol specifications for each transition 4. Risk assessment for each handoff point 5. Recommendations for rebalancing initiative if needed
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.