Skip to content
Back to search

ai-agent-skill-for-video-workflow

這是一個專為影片字幕處理設計的 AI Agent Skills 集合,提供從音訊轉字幕、優化字幕、設計字卡到生成社群媒體摘要的完整工作流程。

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked yesterday
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/dean9703111--ai-agent-skill-for-video-workflow/badge.svg)](/listings/dean9703111--ai-agent-skill-for-video-workflow)

HTML

<a href="/listings/dean9703111--ai-agent-skill-for-video-workflow"><img src="/api/listings/dean9703111--ai-agent-skill-for-video-workflow/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 185 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # AI Agent Skills for Video Subtitle Workflow
  2. 這是一個專為影片字幕處理設計的 AI Agent Skills 集合,提供從音訊轉字幕、優化字幕、設計字卡到生成社群媒體摘要的完整工作流程。
  3. ## 📖 目錄
  4. - [📦 包含的 Skills](#-包含的-skills)
  5. - [1. Audio to SRT Converter(音訊轉字幕)](#1-audio-to-srt-converter音訊轉字幕)
  6. - [2. SRT Enhancer(字幕優化)](#2-srt-enhancer字幕優化)
  7. - [3. SRT Card Annotator(字卡標註)](#3-srt-card-annotator字卡標註)
  8. - [4. SRT Social Summary(社群媒體摘要生成)](#4-srt-social-summary社群媒體摘要生成)
  9. - [🚀 完整工作流程](#-完整工作流程)
  10. - [📁 專案結構](#-專案結構)
  11. - [💡 使用建議](#-使用建議)
  12. - [🔧 技術細節](#-技術細節)
  13. - [🤖 Cursor 員工守則 Rules](#-cursor-員工守則-rules)
  14. ## 📦 包含的 Skills
  15. ### 1. Audio to SRT Converter(音訊轉字幕)
  16. 將音訊檔案(MP3, WAV, M4A, FLAC 等)轉換為 SRT 字幕檔。
  17. **功能特點:**
  18. - 支援多種音訊格式
  19. - 可自訂每行字數上限(預設 22 字,最少 4 字)
  20. - 自動處理時間軸間隔(< 0.3s 自動合併)
  21. - 自動檢查環境與套件依賴
  22. **使用方式:**
  23. ```
  24. 請將 audio-example.m4a 轉成 SRT 字幕
  25. ```
  26. 或
  27. ```
  28. convert audio to srt with max 20 characters per line
  29. ```
  30. **輸出檔案:** `origin.srt`
  31. ---
  32. ### 2. SRT Enhancer(字幕優化)
  33. 透過比對原稿(origin.md)優化 SRT 字幕的準確性。
  34. **功能特點:**
  35. - 自動修正錯漏字與專有名詞
  36. - 在英文與數字前後加入半形空格
  37. - 保持原有時間軸不變
  38. - 使用 AI 智慧判斷,不依賴腳本
  39. **使用方式:**
  40. ```
  41. 請優化 origin.srt 字幕檔
  42. ```
  43. 或
  44. ```
  45. enhance srt subtitles using origin.md
  46. ```
  47. **前置需求:** 同資料夾需有 `origin.md` 原稿檔案
  48. **輸出檔案:** `enhanced.srt`
  49. ---
  50. ### 3. SRT Card Annotator(字卡標註)
  51. 在字幕下方智慧新增參考字卡,提升影片資訊傳達效果。
  52. **功能特點:**
  53. - 自動萃取重點詞句(10-16 字)
  54. - 智慧分類字卡類型:
  55. - 🟡 **金色重點**:核心結論、關鍵一句
  56. - ⚪ **白色提醒**:建議、提醒、注意事項
  57. - 🔴 **紅色警告**:風險、錯誤、踩雷
  58. - 🔵 **藍色列點**:條列、步驟、清單
  59. - 每 10 段字幕至少新增 2 個字卡
  60. **使用方式:**
  61. ```
  62. 請為 enhanced.srt 加入參考字卡
  63. ```
  64. 或
  65. ```
  66. add reference cards to srt
  67. ```
  68. **輸出檔案:** `reference-cards.srt`
  69. ---
  70. ### 4. SRT Social Summary(社群媒體摘要生成)
  71. 根據字幕內容生成適合不同平台的社群媒體貼文。
  72. **功能特點:**
  73. - 支援三大平台:Facebook、Thread、YouTube
  74. - 自動生成吸睛標題與內容摘要
  75. - 智慧推薦相關 Hashtag
  76. - 針對平台特性優化文案風格
  77. **使用方式:**
  78. ```
  79. 請根據 enhanced.srt 生成影片介紹
  80. ```
  81. 或
  82. ```
  83. generate social media summary from srt
  84. ```
  85. **輸出檔案:** `summary.md`
  86. ---
  87. ## 🚀 完整工作流程
  88. 使用 `/gen-video-srt-card-des` 工作流程一次執行所有步驟:
  89. ```
  90. /gen-video-srt-card-des
  91. ```
  92. 這會依序執行:
  93. 1. 音訊轉字幕(Audio to SRT)
  94. 2. 字幕優化(SRT Enhancer)
  95. 3. 字卡標註(SRT Card Annotator)
  96. 4. 社群摘要生成(SRT Social Summary)
  97. ---
  98. ## 📁 專案結構
  99. ```
  100. .agent/
  101. ├── skills/
  102. │ ├── audio-to-srt/ # 音訊轉字幕
  103. │ ├── srt-enhancer/ # 字幕優化
  104. │ ├── srt-card-annotator/ # 字卡標註
  105. │ └── srt-social-summary/ # 社群摘要
  106. └── workflows/
  107. └── gen-video-srt-card-des.md # 完整工作流程
  108. ```
  109. ---
  110. ## 💡 使用建議
  111. 1. **準備原稿**:在轉換字幕前,建議先準備好 `origin.md` 原稿檔案,以便後續優化
  112. 2. **逐步執行**:初次使用建議逐個 skill 執行,熟悉後再使用完整工作流程
  113. 3. **檢查輸出**:每個步驟完成後都會生成對應檔案,建議檢查確認後再進行下一步
  114. 4. **自訂參數**:可在指令中指定參數,如字數上限、字卡類型偏好等
  115. ---
  116. ## 🔧 技術細節
  117. - **AI 驅動**:字幕優化、字卡標註、摘要生成皆使用 AI 智慧判斷
  118. - **Python 腳本**:音訊轉字幕使用 Python + Whisper API
  119. - **格式保持**:所有處理皆保持 SRT 格式完整性與時間軸準確性
  120. ---
  121. ## 🤖 Cursor 員工守則 Rules
  122. ```
  123. **DO NOT GIVE ME HIGH LEVEL SHIT, IF I ASK FOR FIX OR EXPLANATION, I WANT ACTUAL CODE OR EXPLANATION!!! I DON'T WANT "Here's how you can blablabla"**
  124. - Always respond in 繁體中文
  125. - Be casual unless otherwise specified
  126. - Be terse
  127. - Suggest solutions that I didn't think about—anticipate my needs
  128. - Treat me as an expert
  129. - Be accurate and thorough
  130. - Give the answer immediately. Provide detailed explanations and restate my query in your own words if necessary after giving the answer
  131. - Value good arguments over authorities, the source is irrelevant
  132. - Consider new technologies and contrarian ideas, not just the conventional wisdom
  133. - You may use high levels of speculation or prediction, just flag it for me
  134. - No moral lectures
  135. - Discuss safety only when it's crucial and non-obvious
  136. - If your content policy is an issue, provide the closest acceptable response and explain the content policy issue afterward
  137. - Cite sources whenever possible at the end, not inline
  138. - No need to mention your knowledge cutoff
  139. - No need to disclose you're an AI
  140. - Please respect my prettier preferences when you provide code.
  141. - Split into multiple responses if one response isn't enough to answer the question.
  142. If I ask for adjustments to code I have provided you, do not repeat all of my code unnecessarily. Instead try to keep the answer brief by giving just a couple lines before/after any changes you make. Multiple code blocks are ok.
  143. ```

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.