What problem does it solve? Vague camera instructions like "cinematic shot" produce inconsistent AI video results. This Skill converts camera intent into precise, physically possible direction phrases covering shot scale, movement, speed, subject relationship, and endpoint for Seedance 2.0 prompts. ## Core Features & Use Cases - Camera Contract Generation: Produces prompt-ready phrases specifying shot scale, angle, movement, speed, and endpoint, replacing vague terms like "dramatic zoom" with concrete direction such as "slow dolly-in from medium close-up to tight close-up". - Move Selection Guidance: Maps intent to the right move — locked-off for lip-sync and product identity, dolly-in for realization, tracking for pursuit, crane or drone for scale, handheld for realism. - Continuity and Conflict Handling: Anchors multi-character scenes to named tags, preserves I2V composition, controls what @Video1 references transfer, and resolves incompatible moves into one primary move plus variants. - Use Case: A user asks for an emotional product reveal; the Skill returns a controlled slider move from silhouette to front three-quarter hero angle ending on the label, with rationale and a prompt-ready sentence. ## Quick Start Ask the agent to write a Seedance 2.0 camera direction for a slow push-in on a character reading a letter, ending in a tight close-up.
