Avatar Reel Composer

Orchestrates the sibling skills into one finished reel from a script + an existing avatar, replicating the structure of the avatar's analyzed reels. An optional finishing pass (finish_reel.py) adds burned-in word-timed subtitles + a music bed ducked under the voice. SFX stingers and dissolves are still deferred (see Next phases).

When to use

• The user has an avatar folder (e.g. lolo/) that already contains videos/, a trained voice in voices/, camera-angle images in angles/, and ideally a talking_profile.json (all produced by the upstream skills below).
• They give you a script (what the avatar should say) and want a vertical reel where the avatar's voice narrates continuously while the video cuts between talking-head shots and complementary B-roll — exactly like the original reels analyzed by video-scene-analysis.