The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with `ovs plan validate`.
安装
npx skills add Orkas-AI/Orkas-VideoStudio --skill stage-plannpx skills add Orkas-AI/Orkas-VideoStudio --skill stage-plan -a claude-code -gnpx skills add Orkas-AI/Orkas-VideoStudio --skill stage-plan -a codex -ggemini skills install https://github.com/Orkas-AI/Orkas-VideoStudio.git --path packages/skills/stage-plangh skill install Orkas-AI/Orkas-VideoStudio stage-plangit 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-plan ~/.claude/skills/stage-plan # Claude Code
cp -R /tmp/Orkas-AI__Orkas-VideoStudio/packages/skills/stage-plan ~/.agents/skills/stage-plan # Codex, Cursor, Gemini CLI, Copilot, OpenCode