Stats
Actions
Tags
Provides patterns and guidelines for AI transparency including confidence indicators, source attribution, reasoning traces, and limitation disclosures. Useful for trustworthy AI UIs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ai-alignment-reasoning:transparency-patternsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Transparency in AI products means making the system's knowledge, limitations, and confidence visible to users. It's how you build warranted trust — trust based on understanding, not blind faith.
Transparency in AI products means making the system's knowledge, limitations, and confidence visible to users. It's how you build warranted trust — trust based on understanding, not blind faith.
Too much transparency overwhelms. Too little erodes trust. Calibrate by:
npx claudepluginhub owl-listener/ai-design-skills --plugin ai-alignment-reasoningGuides progressive disclosure of AI capabilities to align with user mental models, using strategies like on-demand hints, escalating examples, and layered revelation for AI product design.
Calibrates AI confidence to evidence, flagging uncertainty and limitations before presenting conclusions. Useful when accuracy matters or knowledge is partial.
Implements EU AI Act Arts. 13-14 and GDPR Arts. 13-14 transparency requirements for AI systems: user notifications, capability disclosures, limitations, and automated logic explanations. Useful for compliant AI apps.