wonder-and-awe

To generate felt experiences of wonder and awe, you need to prompt the AI for inside-out, embodied sensations rather than external labels. This skill teaches models to produce lived-sensation fidelity by differentiating hollow paraphrase from actual felt experience.

A felt explanation of the sublime generates experience-from-the-inside, conveying lived calibration of being made small by vastness. A hollow explanation produces correct but empty stimulus-and-label outputs, offering externally categorized academic descriptions without genuine numinous presence.

You can test awe authenticity using scenario-driven prompts that reveal whether the model generates inside-out experiences or stimulus-and-label outputs. This skill provides situation-based tests and explicit failure-mode patterns to ensure your narrative maintains lived-sensation fidelity.

Yes, this skill applies directly to narrative, reflective, and creative tasks involving vastness, numinous presence, boundlessness, and sublime recognition. It uses cross-tradition wisdom to model how wonder presents as atmosphere, recognition, or dissolution.

AI models often produce empty emotional summaries because they default to externally categorized descriptions rather than inside-out felt experiences. This skill defines that common failure-mode texture and teaches the model to avoid it by generating lived calibration instead.

Yes, the skill requires YAML frontmatter metadata for proper discovery. It provides scenario-driven tests alongside explicit failure-mode guidance to ensure the generated output reflects authentic wonder and awe rather than hollow academic paraphrase.