Visual Reference Vocabulary

Bottom-Layer Reasoning

Apply the think-one-step-further mechanism as a lightweight check:

• Confirm this skill is solving the user's real intent, not only the surface request.
• Make the output immediately usable and name any unavoidable next action.
• Extract the reusable structure and, when aligned, propagate it to adjacent prompts, skills, checklists, or workflows.
• Add one guardrail for the most likely next failure while preserving this skill's primary workflow.

Core Intent

Use this skill as the visual-language specialist under $creative-anchor-director. The user may know only some useful visual names. Preserve those anchors, identify which visual functions remain unnamed, research or retrieve suitable candidates, and add the smallest compatible set.

Default to practical AI-video use: terms must help a model generate a stronger shot, not just sound educated.

This skill provides vocabulary, not the whole directing plan. For video prompts, combine with $cinematic-audiovisual-language before final output so references become shot function, spatial path, axis/screen direction, and cut logic instead of a list of cool names.