Designs behavioral guardrails for AI products: defines boundaries for content, actions, tone, scope, confidence. Covers specs, rationales, UX, edge cases, refusal templates, and testing scenarios.
npx claudepluginhub owl-listener/ai-design-skills --plugin ai-alignment-reasoningThis skill uses the workspace's default tool permissions.
Guardrails are the behavioral boundaries that define what an AI product will and won't do. They're not just safety constraints — they're design decisions that shape the entire user experience.
Guides designing informed consent, opt-out options, and human override mechanisms for AI products using data or taking actions.
Implements safety guardrails for LLM apps: OpenAI Moderation API content moderation, jailbreak prevention, prompt injection defense, PII detection, topic guardrails, output validation. For production AI with user content.
Structures AI/ML product planning with canvas for user problems, model/task selection, data needs, evaluation metrics, and responsible AI checks. For LLM integrations and AI features.
Share bugs, ideas, or general feedback.
Guardrails are the behavioral boundaries that define what an AI product will and won't do. They're not just safety constraints — they're design decisions that shape the entire user experience.
Every guardrail is a product decision with tradeoffs:
For each guardrail, define:
How the AI communicates a guardrail matters as much as the guardrail itself: