ai-design-skills

failure-taxonomy

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

longitudinal-measurement

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

consent-and-agency

Designing for informed user consent, opt-out, and human override.

comparative-evaluation

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

frustration-detection

Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.

prompt-versioning

Managing prompt iterations, testing changes, and tracking what works.

context-engineering

Designing what information goes into the context window and in what order.

handoff-protocols

Designing smooth transitions between agents and between AI and humans.

cultural-adaptation

Adapting AI behavior for different cultural contexts, languages, and norms.

transparency-patterns

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

cultural-adaptation

Adapting AI behavior for different cultural contexts, languages, and norms.

chain-of-thought-design

Designing reasoning chains that produce better outputs.

user-satisfaction-signals

Interpreting implicit and explicit feedback — edits, regenerations, abandonment.

emotional-design

How the AI responds to user frustration, confusion, delight, and distress.

conversation-patterns

Turn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.

observability-design

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

agent-role-design

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

template-design

Creating reusable, parameterised prompt templates for consistent outputs.

context-window-design

Designing around token limits, memory, and conversation persistence.

guardrail-design

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

trust-calibration

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

task-decomposition

Breaking complex user goals into subtasks that agents can handle.

value-specification

Translating organisational values and user expectations into system constraints.

domain-voice

Tailoring AI behavior for specific professional domains.

guardrail-design

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