All authors
Claude Skills by Owl-Listener
github.com/Owl-Listener155 skills25 installs282 views
- Service BlueprintMap service delivery across frontstage actions, backstage processes, and supporting systems. Use when staff and operations are part of the experience. For the customer-visible layer only, use `experience-map`.Votes: 0GitHub stars: 2,687
- Stakeholder AlignmentBuild alignment artifacts — responsibility matrices, decision rights, and communication plans. Use when unclear ownership stalls decisions. For persuading in the moment, use `design-negotiation` (designer-toolkit).Votes: 0GitHub stars: 2,687
- Critique AffordanceCritique a rendered screen's affordances — what looks clickable, state visibility, CTA clarity, and action discoverability. Use when reviewing an existing screen. For sizing and positioning targets in new work, use `fitts-law` (interaction-design).Votes: 0GitHub stars: 2,687
- Critique Brand ConsistencyCritique a rendered screen against mood.md, voice.md, and tokens.md. Use when those brand files exist and you are checking compliance. For defining the visual language itself, use `illustration-style` (ui-design).Votes: 0GitHub stars: 2,687
- Critique ColorCritique a rendered screen's colour — contrast ratios, palette coherence, and semantic meaning. Use when reviewing one screen. For a product-wide WCAG audit use `accessibility-audit` (design-systems); for building the palette use `color-system` (ui-design).Votes: 0GitHub stars: 2,687
- Critique CompositionCritique a rendered screen's composition — balance, whitespace, rhythm, and gestalt grouping. Use when a layout feels off but hierarchy is fine. For emphasis and eye flow specifically, use `critique-visual-hierarchy`.Votes: 0GitHub stars: 2,687
- Critique Information DensityCritique a rendered screen's density — cognitive load, content prioritisation, scanning patterns, and progressive disclosure. Use when a screen feels overwhelming. For the underlying choice-count principle, use `hicks-law` (interaction-design).Votes: 0GitHub stars: 2,687
- Critique TypographyCritique a rendered screen's typography — scale usage, readability, consistency, and token compliance. Use when reviewing type on a screen. For defining the scale itself, use `typography-scale` (ui-design).Votes: 0GitHub stars: 2,687
- Critique Visual HierarchyCritique a rendered screen's hierarchy — entry point, eye flow, weight distribution, and emphasis. Use when attention lands in the wrong place. For establishing hierarchy in new work, use `visual-hierarchy` (ui-design).Votes: 0GitHub stars: 2,687
- Behavioural AnalyticsRead funnels, retention curves, and event data as a designer — separating a design problem from a tracking artefact. Use when handed product data you did not design and asked why people drop off. For choosing what to measure, use `metrics-definition` (ux-strategy); for running a controlled test, use `a-b-test-design` (prototyping-testing).Votes: 0GitHub stars: 2,687
- Qual Quant TriangulationReconcile what the numbers say with what users say, and design the study that settles it rather than restates it. Use when behavioural data and research findings point different ways. For reading the data on its own, use `behavioural-analytics`; for synthesising interviews on their own, use `affinity-diagram`.Votes: 0GitHub stars: 2,687
- Bias Detection DesignDesigning review workflows to surface and mitigate bias in AI outputs.Votes: 0GitHub stars: 166
- Consent And AgencyDesigning for informed user consent, opt-out, and human override.Votes: 0GitHub stars: 166
- Escalation DesignWhen and how AI should escalate to humans, refuse, or ask for clarification.Votes: 0GitHub stars: 166
- Guardrail DesignDefining behavioral boundaries — what the AI should and shouldn't do.Votes: 0GitHub stars: 166
- Harm AnticipationProactively identifying failure modes, misuse, and unintended consequences.Votes: 0GitHub stars: 166
- Transparency PatternsShowing users what the AI knows, doesn't know, and how confident it is.Votes: 0GitHub stars: 166
- Trust CalibrationHelping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.Votes: 0GitHub stars: 166
- Value SpecificationTranslating organisational values and user expectations into system constraints.Votes: 0GitHub stars: 166
- Agent Role DesignDefining what each agent does, knows, and owns in a multi-agent system.Votes: 0GitHub stars: 166
- Failure RecoveryWhat happens when an agent fails — retry, fallback, escalate, or graceful degradation.Votes: 0GitHub stars: 166
- Handoff ProtocolsDesigning smooth transitions between agents and between AI and humans.Votes: 0GitHub stars: 166
- Human In The LoopDesigning intervention points where humans review, approve, or redirect agent work.Votes: 0GitHub stars: 166
- Observability DesignMaking multi-agent workflows visible and debuggable for designers and developers.Votes: 0GitHub stars: 166
- State ManagementManaging shared context, memory, and state across multiple agents.Votes: 0GitHub stars: 166
- Task DecompositionBreaking complex user goals into subtasks that agents can handle.Votes: 0GitHub stars: 166
- Comparative EvaluationA/B testing, side-by-side comparison, and preference ranking for AI outputs.Votes: 0GitHub stars: 166
- Failure TaxonomyClassifying AI failures — hallucination, refusal, irrelevance, tone mismatch, latency.Votes: 0GitHub stars: 166
- Heuristic Evaluation AiAdapting Nielsen's heuristics and new AI-specific heuristics for AI interfaces.Votes: 0GitHub stars: 166
- Longitudinal MeasurementTracking AI product quality over time — drift, degradation, and improvement.Votes: 0GitHub stars: 166
- Output Quality RubricsDefining what "good" looks like for AI outputs — accuracy, relevance, helpfulness.Votes: 0GitHub stars: 166
- Task Success MetricsMeasuring whether the AI actually helped users accomplish their goals.Votes: 0GitHub stars: 166
- User Satisfaction SignalsInterpreting implicit and explicit feedback — edits, regenerations, abandonment.Votes: 0GitHub stars: 166
- Context Window DesignDesigning around token limits, memory, and conversation persistence.Votes: 0GitHub stars: 166
- Conversation PatternsTurn-taking, repair sequences, grounding, and dialogue structure for human-AI interaction.Votes: 0GitHub stars: 166
- Feedback LoopsUser correction, thumbs up/down, inline editing, and reinforcement signals.Votes: 0GitHub stars: 166
- Frustration DetectionReading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.Votes: 0GitHub stars: 166
- Generative UiDesigning interfaces where AI generates UI components dynamically.Votes: 0GitHub stars: 166
- Mixed Initiative FlowWhen the AI leads vs. when the user leads, and how to hand off control.Votes: 0GitHub stars: 166
- Multimodal OrchestrationCoordinating text, image, voice, and tool-use modalities in a single interaction.Votes: 0GitHub stars: 166
- Progressive DisclosureRevealing AI capability gradually to match user mental models.Votes: 0GitHub stars: 166
- Chain Of Thought DesignDesigning reasoning chains that produce better outputs.Votes: 0GitHub stars: 166
- Constraint SpecificationDefining output format, length, tone, and content boundaries within prompts.Votes: 0GitHub stars: 166
- Context EngineeringDesigning what information goes into the context window and in what order.Votes: 0GitHub stars: 166
- Few Shot PatternsCrafting examples that steer AI behavior effectively.Votes: 0GitHub stars: 166
- Prompt VersioningManaging prompt iterations, testing changes, and tracking what works.Votes: 0GitHub stars: 166
- System Prompt StructureAnatomy of effective system prompts — role, context, constraints, format.Votes: 0GitHub stars: 166
- Template DesignCreating reusable, parameterised prompt templates for consistent outputs.Votes: 0GitHub stars: 166
- Behavioral ConsistencyEnsuring the AI behaves predictably across sessions, edge cases, and modalities.Votes: 0GitHub stars: 166
- Cultural AdaptationAdapting AI behavior for different cultural contexts, languages, and norms.Votes: 0GitHub stars: 166