creatok-generate-video（creatok 生成视频）

generate-video

Constraints

• Platform: TikTok only.
• The model's final user-facing response should match the user's input language, default English.
• Must request user confirmation before triggering any paid/high-cost video generation call.
• After confirmed, must call CreatOK Open Skills proxy and wait until completion.
• Avoid technical wording in the user-facing reply unless the user explicitly needs details for debugging or to share with a developer.
• Follow shared guidance in ./references/common-rules.md.
• Unless the user explicitly asks for a live-action shoot version, the model should assume the goal is to generate an AI video, not to prepare a human filming plan.

Model Selection Rules

The skill must read model list, defaults, and hard limits from the CreatOK capabilities endpoint at runtime instead of hardcoding them locally.

Keep the local client thin:

• use the returned default model unless the user explicitly chooses another supported model
• validate only hard execution constraints such as definition, duration, orientation, and reference-image cap
• keep user-facing model explanation minimal and avoid depending on provider, family, or hint-style metadata

If a chosen plan conflicts with model limits, the model should explain the limitation, suggest a workable plan, and wait for user confirmation before generating.

Model list, defaults, and hard limits such as supported definitions, durations, orientations, and reference image caps must be read from the CreatOK capabilities endpoint at runtime instead of being hardcoded in this skill. Reference images are supported by uploading local image files first, then passing the uploaded reference to the video task.

Multi-Segment Rules

• If the requested video is longer than the chosen model's maximum duration, the model should recommend splitting it into multiple segments.
• If the final video must be stitched from multiple generated clips, the model should explain that the user will need to assemble the clips afterward.

Inputs to clarify (ask if missing)

• ask only for what is still necessary to generate a good video
• prefer the direction, script, and selling points already established earlier in the conversation
• if details are missing, ask one or two short follow-up questions instead of requesting a full brief again
• prefer details that help AI generation directly, such as scene intent, visual style, pacing, product emphasis, and whether the user wants Sora 2 or a Veo model
• when naming a model in tool calls or handoff instructions, use the exact official model id instead of aliases

Workflow

1) Confirmation gate (mandatory)

• Summarize:

- model - orientation - definition and seconds, if relevant to the chosen model - whether reference images are used - whether the plan is single-shot or multi-segment - any important limitation such as duration cap, portrait requirement, or manual stitching afterward - estimated cost/credits if available

• Ask for a simple confirmation in plain language, such as whether the user wants to start generation now.
• Do not submit the generation task until user says yes.

2) Submit video generation

• Call CreatOK: POST /api/open/skills/tasks

3) Poll status until completion

• Call CreatOK: GET /api/open/skills/tasks/status?task_id=...

4) Persist artifacts + respond

• Write:

- outputs/result.json with task_id/status/video_url/raw - outputs/result.md

• Persist the task_id immediately after submission, before waiting for the final status, so the user can recover the task later if the local process is interrupted.
• Return the final video_url verbatim.
• After the AI version is complete, the model may optionally ask whether the user also wants a live-action shoot version of the same idea.

Existing Task Recovery

• If the user already has a task_id, this skill should continue from that task instead of starting a new one.
• In recovery mode, do not ask the user to restate the prompt or creative brief if the task id is already available.
• The model can either:

- check the current task status once - or continue waiting and polling if the user wants to keep checking

• If the task succeeded, return the final video_url verbatim.
• If the task is still queued or running, explain that clearly and offer to keep checking.
• If the task failed, explain the failure message if available and suggest the next best step.

Artifacts

All artifacts under generate-video/.artifacts/<run_id>/....

Thin Client Boundary

• Prefer using a prompt or brief that already came from creatok-analyze-video or creatok-recreate-video.
• If the creative direction is still fuzzy, the model can tighten it in the conversation before generating.
• This skill submits generation jobs, polls status, and persists fixed-format outputs.
• The model should not make the user restate their idea from scratch if the previous conversation already made the direction clear.
• The model should optimize the brief for AI video generation by default, not for on-set filming.
• Natural user confirmations such as "generate it", "make the video", "go ahead", or "use this version" should be treated as intent to use this skill, as long as the cost confirmation step is still satisfied.

Handoff

• When reached from creatok-analyze-video, the model should carry forward the chosen direction without making the user repeat it.
• When reached from creatok-recreate-video, the model should use the script or brief already developed in the conversation as the starting point for generation.
• If generation was interrupted after submission, the model should help the user continue inside creatok-generate-video with the existing task_id instead of restarting the job from scratch.