global-clip-forge 是做什麼的？
長篇 YouTube 訪談/談話/播客 → 5–8 個雙語硬字幕短片：使用 yt-dlp + Whisper 備援 + AI 翻譯 + PNG 疊加字幕燒錄（無需 libass）。附 README 展示截圖。
將長篇 YouTube 訪談/談話/播客轉換為 5–8 個雙語硬字幕短片：使用 yt-dlp + Whisper 備援 + AI 翻譯 + PNG 疊加字幕燒錄（無需 libass）。附 README 展示截圖。
此技能專為處理長篇 YouTube 影片（如訪談、談話節目或播客）而設計，能自動將其分割為 5 至 8 個精華短片，並為每個短片添加雙語（原文 + 中文翻譯）硬字幕。它結合了 yt-dlp 下載影片、Whisper 進行語音辨識（含備援機制）、AI 翻譯引擎，以及使用 PNG 圖像疊加技術直接將字幕燒錄到影片中，無需依賴 libass 等外部字體渲染庫。支援的多平台適用性使其能作為 AI 代理（如 Claude Code、Cursor、Codex）的技能使用，開發者只需提供 YouTube 連結即可自動化整個剪輯與字幕流程。最終輸出可直接用於社群媒體分享，大幅提升內容在地化的效率。
npx skills add quynj/global-clip-forge長篇 YouTube 訪談/談話/播客 → 5–8 個雙語硬字幕短片：使用 yt-dlp + Whisper 備援 + AI 翻譯 + PNG 疊加字幕燒錄（無需 libass）。附 README 展示截圖。
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.