Deterministically assemble an approved cross-modal EDL (plan.json) into a finished video — produce each segment (edit/compose/generate/provided, delegated to its line), then assemble in ffmpeg tiers: concat primaries → overlay composed layers → mix narration once (coverage check) → burn captions → verify loudness; idempotent-resumable, with QA before the draft gate.
安装
npx skills add Orkas-AI/Orkas-VideoStudio --skill stage-assemblenpx skills add Orkas-AI/Orkas-VideoStudio --skill stage-assemble -a claude-code -gnpx skills add Orkas-AI/Orkas-VideoStudio --skill stage-assemble -a codex -ggemini skills install https://github.com/Orkas-AI/Orkas-VideoStudio.git --path packages/skills/stage-assemblegh skill install Orkas-AI/Orkas-VideoStudio stage-assemblegit clone --depth 1 https://github.com/Orkas-AI/Orkas-VideoStudio /tmp/Orkas-AI__Orkas-VideoStudio
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Orkas-AI__Orkas-VideoStudio/packages/skills/stage-assemble ~/.claude/skills/stage-assemble # Claude Code
cp -R /tmp/Orkas-AI__Orkas-VideoStudio/packages/skills/stage-assemble ~/.agents/skills/stage-assemble # Codex, Cursor, Gemini CLI, Copilot, OpenCode