ai-design-skills
AI Design Skills Collection: agentic skills, commands, and plugins for designing AI products — from interaction patterns to alignment, evaluation, agent orchestration, and prompt architecture.
440
Install command
npx skhub add --skillset @owl-listener/ai-design-skillsIncluded Skills
Ensuring the AI behaves predictably across sessions, edge cases, and modalities.
00
Designing review workflows to surface and mitigate bias in AI outputs.
00
Designing reasoning chains that produce better outputs.
00
A/B testing, side-by-side comparison, and preference ranking for AI outputs.
00
Designing for informed user consent, opt-out, and human override.
00
Creating reusable, parameterised prompt templates for consistent outputs.
00
Adjusting formality, warmth, confidence, and style per context.
00
Defining what each agent does, knows, and owns in a multi-agent system.
00
Defining output format, length, tone, and content boundaries within prompts.
00
Designing what information goes into the context window and in what order.
00
Designing around token limits, memory, and conversation persistence.
00
Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.
00
Adapting AI behavior for different cultural contexts, languages, and norms.
00
Tailoring AI behavior for specific professional domains.
00
How the AI responds to user frustration, confusion, delight, and distress.
00
How the AI communicates mistakes, uncertainty, and limitations gracefully.
00
When and how AI should escalate to humans, refuse, or ask for clarification.
00
What happens when an agent fails — retry, fallback, escalate, or graceful degradation.
00
Classifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.
00
User correction, thumbs up/down, inline editing, and reinforcement signals.
00
Crafting examples that steer AI behavior effectively.
00
Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.
00
Designing interfaces where AI generates UI components dynamically.
00
Defining behavioral boundaries — what the AI should and shouldn't do.
00
Designing smooth transitions between agents and between AI and humans.
00
Proactively identifying failure modes, misuse, and unintended consequences.
00
Adapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.
00
Designing intervention points where humans review, approve, or redirect agent work.
00
Tracking AI product quality over time — drift, degradation, and improvement.
00
When the AI leads vs. when the user leads, and how to hand off control.
00
Coordinating text, image, voice, and tool-use modalities in a single interaction.
00
Making multi-agent workflows visible and debuggable for designers and developers.
00
Defining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.
00
Defining AI character, voice, and personality traits.
00
Revealing AI capability gradually to match user mental models.
00
Managing prompt iterations, testing changes, and tracking what works.
00
Managing shared context, memory, and state across multiple agents.
00
Anatomy of effective system prompts — role, context, constraints, format.
00
Breaking complex user goals into subtasks that agents can handle.
00
Measuring whether the AI actually helped users accomplish their goals.
00
Showing users what the AI knows, doesn't know, and how confident it is.
00
Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.
00
Interpreting implicit and explicit feedback — edits, regenerations, abandonment.
00
Translating organisational values and user expectations into system constraints.
00