Verify existing media alignment evidence and flag ambiguous, unsafe, or unreliable matches before you trust them. Deterministic, precision-first QC with JSON and Markdown reports — no AI guessing.
我長期處理中英夾雜的技術型影音內容（教學影片、會議與簡報錄音），很清楚這類素材最頭痛的就是專有名詞和英文縮寫被聽錯。這個 Skill 把我實際在用的整套做法工具化：以 faster-whisper 在本機 CPU 就能轉錄（免 GPU、免雲端 API、免費），並用「轉錄前餵專有名詞提示＋轉錄後批次修正同音錯字」兩道工序把準確率拉高；YouTube 連結則走「先抓現成字幕、失敗自動改抓音訊轉錄」的穩定路線，最後一併產出 SRT 字幕、逐字稿與帶時間戳的重點摘要。全程本機運算、檔案不上雲，適合在意內容隱私又要快速消化長影音的人。 I work daily with mixed Chinese-English technical audio, where jargon and acronyms get mis-heard most. This Skill packages my workflow: faster-whisper runs locally on CPU (no GPU, no cloud API)
只要輸入你的產業、產品或想拍的主題，自動完成短影音策略、爆點 Hook、口播腳本、拍攝分鏡、字幕、CTA、貼文文案與系列選題，讓你從不知道拍什麼，到拿起手機就能直接開拍。
輸入產品或主題，一次產出「3秒開場鉤子」短影音腳本(含分鏡、口白、字幕)，以及可直接貼上 Seedance 2 / Kling / Runway / Veo 的結構化英文AI影片Prompt。方法論經長庚醫院、成功大學、富士通等企業影片專案實測驗證，主打穩定可複製的產出流程，而非碰運氣的靈感發想。適合電商賣家、KOL、內容代理商每週穩定產出短影音素材。
"A social media content and copywriting skill for TikTok, Instagram, LinkedIn, Facebook, and WhatsApp. Generates captions, video scripts, brand voice guidelines, content calendars, and ad copy using structured copywriting frameworks. For marketers, founders, and agencies."
Analyze an AI video concept before generation, identify likely failure points, and turn it into a more production-ready shot plan with safer prompts and fallback options.
Audits Amazon listing images offline and delivers traceable safe derivatives, evidence reports, and a reconciled ZIP—without paid APIs or acceptance guarantees.