Install
openclaw skills install seedance-story-orchestratorOrchestrate script-to-final-video production with a strict stage-gated workflow (outline → episode_plan → storyboard → storyboard_images → render), using See...
openclaw skills install seedance-story-orchestrator阶段性方案(Phase 1):
seedance-story-orchestratorseedance-video-generation/seedance.py以“可审计、可恢复、可控推进”为第一目标。
固定阶段顺序:
outline -> episode_plan -> storyboard -> storyboard_images -> render
规则:
checkpoint-{stage}.json,默认 confirmed=falserun 会立即停止并返回:
pending_confirmation_stagenext_actionconfirm --stage <stage> 后再继续下一阶段seedance-video-generation skill(必须可访问 seedance.py)ARK_API_KEY# 1) 运行到 render(会在每个关卡停下)
python3 {baseDir}/scripts/run_story.py run \
--project-dir {baseDir}/outputs/my-project \
--input-file /path/to/story.txt \
--stage render
# 2) 按提示确认阶段(示例)
python3 {baseDir}/scripts/run_story.py confirm \
--project-dir {baseDir}/outputs/my-project \
--stage outline
# 3) 查看整体状态
python3 {baseDir}/scripts/run_story.py status \
--project-dir {baseDir}/outputs/my-project
# 首次运行(会停在 outline)
python3 {baseDir}/scripts/run_story.py run \
--project-dir ./my-project \
--input-file ./story.txt \
--stage render
# 逐关确认并继续
python3 {baseDir}/scripts/run_story.py confirm --project-dir ./my-project --stage outline
python3 {baseDir}/scripts/run_story.py run --project-dir ./my-project --stage render
python3 {baseDir}/scripts/run_story.py confirm --project-dir ./my-project --stage episode_plan
python3 {baseDir}/scripts/run_story.py run --project-dir ./my-project --stage render
python3 {baseDir}/scripts/run_story.py confirm --project-dir ./my-project --stage storyboard
python3 {baseDir}/scripts/run_story.py run --project-dir ./my-project --stage render
python3 {baseDir}/scripts/run_story.py confirm --project-dir ./my-project --stage storyboard_images
python3 {baseDir}/scripts/run_story.py run --project-dir ./my-project --stage render
python3 {baseDir}/scripts/run_story.py confirm --project-dir ./my-project --stage render
最终视频路径:
./my-project/videos/run-YYYYMMDD-HHMMSS/final-video.mp4
# 先生成 sub-agent 任务
python3 {baseDir}/scripts/build_subagent_task.py \
--input-file /path/to/raw.txt \
--output {baseDir}/outputs/subagent-task.txt
# 用 sessions_spawn 执行后,拿到结构化 JSON,再喂给 prepare
python3 {baseDir}/scripts/prepare_storyboard.py \
--input-file /path/to/subagent-output.json \
--output-dir {baseDir}/outputs
python3 {baseDir}/scripts/prepare_storyboard.py \
--input-file /path/to/story.txt \
--output-dir {baseDir}/outputs
python3 {baseDir}/scripts/prepare_storyboard.py \
--staged-artifacts /path/to/staged-artifacts.v1.json \
--output-dir {baseDir}/outputs
python3 {baseDir}/scripts/prepare_storyboard.py \
--input-file /path/to/story.txt \
--output-dir {baseDir}/outputs
python3 {baseDir}/scripts/seedream_image.py storyboard \
--storyboard /path/to/storyboard.draft.v1.json \
--output-dir {baseDir}/outputs/images
python3 {baseDir}/scripts/orchestrate_story.py run \
--storyboard /path/to/storyboard.draft.v1.json \
--output-dir {baseDir}/outputs/videos
python3 {baseDir}/scripts/concat_videos.py \
--run-dir {baseDir}/outputs/videos/run-YYYYMMDD-HHMMSS
主要产物:
plan-*/storyboard.draft.v1.jsonplan-*/assets.v1.jsonplan-*/staged-artifacts.v1.jsoncheckpoint-{stage}.jsonvideos/run-*/result-index.jsonvideos/run-*/run-summary.jsonvideos/run-*/final-video.mp4references/storyboard-v1.schema.jsonreferences/assets-v1.schema.jsonreferences/staged-artifacts-v1.schema.jsonreferences/subagent-parser-contract.mddocs/design-doc-v0.2.0-phase1.mddocs/logic-flow-v0.2.0-phase1.mdrun_story.py 已内置混合日志 JSON 解析与严格关卡机制