ai-video-continuationlisted

# AI Video Continuation Continue one short source clip naturally before or after its existing action. Use this Skill when the user already has one source video and asks to continue the next action, hold a moment longer, extend an establishing shot, add a lead-in, complete a reveal, create a natural ending, or generate the next beat of footage that joins the source. ## Scope and adjacent routes The normal route is one source video, one before/after direction, and one extended clip. Route a request to restyle an existing clip into a new visual style to a video-restyle workflow; a request to alter existing frames of the source rather than add new footage to a video-edit workflow; and a request to begin and end on two fixed images to a first-and-last-frame workflow. Keep this route focused on adding matching footage to one source video, not on assembling multiple clips. ## Inputs and defaults The hard inputs are: - one accessible source video the host Agent can inspect; - the continuation direction — add footage before the start or after the end; - the next visual beat the new footage should reach. Ask only for a missing hard input. Reuse the known scene, mood, subject, camera, and source-audio preference. The trusted source duration is itself a hard planning input, because the extension is sized against it. For a local source file the host Agent can access, use the bundled upload helper only after inspection: ```text python3 scripts/mcp_client.py upload ./source-clip.mp