此技能用於在任何平台上創建、改進或疑難排解 Seedance 2.0 影片，包括 Dreamina、Jimeng、CapCut、Doubao、Volcengine/Ark、BytePlus、Runway 的 Seedance 路由、fal，以及第三方供應商/路由器平台，如 EvoLink、OpenRouter、Kie.ai、PiAPI、LaoZhang、Runware、ModelsLab、AI/ML API、MuAPI、SeeGen 和 Segmind。涵蓋文字/圖片/影片/參考轉影片提示、首尾幀、對話、唇形同步與音訊、IP 安全改寫、API、定價和模型 ID 查詢。
This skill, `tenglonghaiwen-hub/zoraagent`, is designed for developers and AI agent users working with Seedance 2.0 video generation. It provides a unified interface for creating, improving, and troubleshooting videos across a wide range of platforms, including mainstream tools like Dreamina, Jimeng, CapCut, Doubao, and Runway, as well as third-party providers like EvoLink, OpenRouter, and Kie.ai. The skill supports various prompt types (text, image, video, reference-to-video), first/last frame control, dialogue and lip-sync features, IP-safe rewrites, and API interactions. It is built to be integrated into agent systems like Claude Code, Cursor, or Codex, enabling automated video workflows. The skill's documentation outlines how to handle pricing, model IDs, and platform-specific nuances, making it a comprehensive tool for Seedance 2.0 video tasks.
npx skills add https://github.com/tenglonghaiwen-hub/zoraagent/tree/main/skills/codex-imports/seedance-20當在任何表面上創建、改進或疑難排解 Seedance 2.0 影片時，應使用此技能 - Dreamina、Jimeng、CapCut、Doubao、Volcengine/Ark、BytePlus、Runway 的 Seedance 路由、fal，或第三方供應商/路由器平台，例如 EvoLink、OpenRouter、Kie.ai、PiAPI、LaoZhang、Runware、ModelsLab、AI/ML API、MuAPI、SeeGen 和 Segmind - 包括文字/圖片/影片/參考轉影片提示、首尾幀、對話、唇形同步與音訊、IP 安全改寫、API、定價和模型 ID 查詢。
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.