Owl-Listener

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Defining behavioral boundaries — what the AI should and shouldn't do.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Proactively identifying failure modes, misuse, and unintended consequences.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Showing users what the AI knows, doesn't know, and how confident it is.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Translating organisational values and user expectations into system constraints.

Owl-Listener/ai-design-skills

Plugin Claude Code

Design multi-agent systems, handoffs between AI agents, and human-in-the-loop workflows.

Owl-Listener/ai-design-skills

Command

Create a human oversight plan for an agentic system.

Owl-Listener/ai-design-skills

Command

Design a complete multi-agent workflow with roles, handoffs, and fallbacks.

Owl-Listener/ai-design-skills

Command

Map out agent responsibilities, boundaries, and communication patterns.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Defining what each agent does, knows, and owns in a multi-agent system.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

What happens when an agent fails — retry, fallback, escalate, or graceful degradation.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Designing smooth transitions between agents and between AI and humans.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Designing intervention points where humans review, approve, or redirect agent work.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Making multi-agent workflows visible and debuggable for designers and developers.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Managing shared context, memory, and state across multiple agents.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Breaking complex user goals into subtasks that agents can handle.

Owl-Listener/ai-design-skills

Plugin Claude Code

Measure AI output quality, user satisfaction, task success, and design effectiveness.

Owl-Listener/ai-design-skills

Command

Build a scoring rubric for evaluating AI output quality.

Owl-Listener/ai-design-skills

Command

Design a benchmark suite to measure AI product performance over time.

Owl-Listener/ai-design-skills

Command

Execute a structured evaluation of an AI feature against defined criteria.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

A/B testing, side-by-side comparison, and preference ranking for AI outputs.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Adapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.

Owl-Listener/ai-design-skills

Skill Claude CodeCodex

Tracking AI product quality over time — drift, degradation, and improvement.