analyzing-videos

yikart/AiToEarn · Agent Skill

分析影片內容，提取精彩片段，建立摘要並生成關鍵詞以獲得更好的理解。

總覽

發布者	yikart組織
儲存庫	yikart/AiToEarn ↗
技能資料夾	`analyzing-videos`
星	25,856
附帶檔案	1
授權	MIT
最近更新	2026年3月16日
連結	技能原始碼 ↗ · 儲存庫 ↗

Mozgi 檢查

我們在技能檔案中發現的內容。詳細資訊需訂閱。

安全性

低風險 · 未發現明顯風險 — 完整報告會顯示細節

相容性

僅含說明 — 適用於多數代理

相似技能

找到 72 個相似技能

訂閱另含

安裝

技能就是一個含 SKILL.md 的資料夾。選擇你的代理，在專案根目錄的終端機（macOS、Linux 或 Windows 的 Git Bash）執行指令。

把提示貼到 Claude、Codex 或其他助理：它會自行檢查並安裝技能。

Install the “analyzing-videos” skill from mozgi.io (https://mozgi.io/skills/analyzing-videos/) for me.

1. Download the archive: https://mozgi.io/skills/analyzing-videos/download
   If it fails, take the skill folder from the source: https://github.com/yikart/AiToEarn/tree/main/project/aitoearn-backend/apps/aitoearn-ai/src/core/agent/skills/analyzing-videos
2. Read SKILL.md and the other files. Check the skill is safe: no hidden commands, no sending data elsewhere, no scripts doing something other than described. If anything looks suspicious, stop and tell me.
3. Put the “analyzing-videos” folder into your agent's skills folder: .claude/skills/ for Claude Code, .agents/skills/ for Codex, .cursor/skills/ for Cursor, .gemini/skills/ for Gemini CLI. Inside the project if we are in one, otherwise in the home folder (~/.claude/skills/ etc.).
4. Make sure <skills folder>/analyzing-videos/SKILL.md exists.
5. Briefly tell me what this skill does and offer to try it on my task.

If you cannot do a step yourself, tell me what to click or type.

git clone --depth 1 --branch main https://github.com/yikart/AiToEarn.git /tmp/AiToEarn
mkdir -p .claude/skills
cp -r /tmp/AiToEarn/project/aitoearn-backend/apps/aitoearn-ai/src/core/agent/skills/analyzing-videos .claude/skills/analyzing-videos

重新啟動 Claude Code — 技能就會出現在清單中，手動呼叫：/analyzing-videos。要套用到所有專案，請放在 ~/.claude/skills。

git clone --depth 1 --branch main https://github.com/yikart/AiToEarn.git /tmp/AiToEarn
mkdir -p .agents/skills
cp -r /tmp/AiToEarn/project/aitoearn-backend/apps/aitoearn-ai/src/core/agent/skills/analyzing-videos .agents/skills/analyzing-videos

Codex 會從目前資料夾往上到儲存庫根目錄，在 .agents/skills 中尋找技能；用 /skills 或 $analyzing-videos 呼叫。所有專案：~/.agents/skills。

git clone --depth 1 --branch main https://github.com/yikart/AiToEarn.git /tmp/AiToEarn
mkdir -p .cursor/skills
cp -r /tmp/AiToEarn/project/aitoearn-backend/apps/aitoearn-ai/src/core/agent/skills/analyzing-videos .cursor/skills/analyzing-videos

Cursor 啟動時會載入技能；在 Agent 聊天輸入「/」呼叫。Cursor 也會讀取 .claude/skills 與 .agents/skills。所有專案：~/.cursor/skills。

git clone --depth 1 --branch main https://github.com/yikart/AiToEarn.git /tmp/AiToEarn
mkdir -p .gemini/skills
cp -r /tmp/AiToEarn/project/aitoearn-backend/apps/aitoearn-ai/src/core/agent/skills/analyzing-videos .gemini/skills/analyzing-videos

任務符合時，Gemini CLI 會提議啟用技能，由你確認。所有專案：~/.gemini/skills。

技能檔案

1 個檔案下載 ZIP

安裝前請先檢視 SKILL.md 與相關檔案。點擊檔案即可預覽。

SKILL.md 內容

作者原文 · 唯讀

Video Analysis

Analyzes video content for understanding and extracts highlight clips using AI multimodal analysis.

When to Use

Use this skill when:

Analyzing video content for summary
Extracting highlight/exciting moments
Generating video keywords and tags
Creating trailers from longer videos
Understanding plot and storyline
Finding viral-worthy moments

Analysis Capabilities

Visual Analysis: Scene detection, object recognition, action identification
Audio Analysis: Speech recognition, music detection, sound effects
Language Understanding: Dialogue analysis, sentiment detection
Multimodal Fusion: Combines all modalities for comprehensive understanding

Workflow

Step 1: Get Source Video

Obtain the video URL to analyze.

Step 2: Submit Analysis Task

Call submitAideoTask with appropriate prompt:

For understanding: "Analyze and summarize this video"
For highlights: "Extract the most exciting moments"

Step 3: Poll for Results

1. First check: Wait 210 seconds after submission

2. Subsequent checks: Wait 30 seconds between polls

3. Call getAideoTaskStatus to check progress

Step 4: Timeout Handling

Maximum wait time: 20 minutes

If task exceeds 20 minutes, report as timeout failure.

Step 5: Return Results

Results vary by task type:

Understanding: Summary, keywords, plot analysis (JSON)
Highlights: Array of highlight clip URLs

Examples

Example 1: Extract Highlights

User request: "Create a 30-second highlight reel from this video"

submitAideoTask:
  prompt: "Extract the most exciting moments from this video to create a 30-second highlight compilation"
  multiInputs: ["source_video.mp4"]

Example 2: Video Understanding

User request: "Analyze this video and give me a summary"

submitAideoTask:
  prompt: "Analyze this video content and generate: summary, keywords, and plot analysis"
  multiInputs: ["video.mp4"]

Example 3: Create Trailer

User request: "Make a trailer from this long video"

submitAideoTask:
  prompt: "Extract the most engaging and exciting moments to create a compelling trailer"
  multiInputs: ["long_video.mp4"]

Example 4: Find Viral Moments

User request: "Find the best clips for social media"

submitAideoTask:
  prompt: "Identify and extract the most viral-worthy moments from this video for social media"
  multiInputs: ["content_video.mp4"]

Output Types

Highlight Extraction

Returns array of clip URLs
Each clip contains exciting/engaging moment
Clips can be used directly or further edited

Video Understanding

Summary: Brief description of video content
Keywords: Relevant tags and topics
Plot Analysis: Story structure and key events

Important Notes

Maximum video length: 2 hours
Maximum wait time: 20 minutes
Highlight extraction returns multiple clip URLs
Understanding returns JSON with summary, keywords, plot
Processing time: ~10 minutes per 1-minute video

常見問題

analyzing-videos 技能有什麼用途？

分析影片內容，提取精彩片段，建立摘要並生成關鍵詞以獲得更好的理解。

如何安裝 analyzing-videos？

打開本頁的「安裝」區塊並選擇你的代理 — Claude Code、Codex、Cursor 或 Gemini CLI：那裡有把技能資料夾複製到正確位置的現成指令。也可以複製「透過助理」分頁中的提示，讓助理自行檢查並安裝技能。

analyzing-videos 適用哪些 AI 模型？

技能是純 Markdown 指示（Agent Skills 格式），因此 analyzing-videos 適用任何讀取 SKILL.md 的代理：Claude Code、Codex、Cursor、Gemini CLI、GitHub Copilot、OpenCode 等。只有在任務符合技能描述時，模型才會載入指示。

analyzing-videos 是免費的嗎？

此技能由 yikart 公開發布，採用 MIT 授權。技能本身免費 — 你只需向 AI 供應商支付實際使用的 token 費用。

安裝技能安全嗎？

技能是代理會遵循的指示，安裝前請閱讀 SKILL.md 及相關檔案。技能資料夾中的腳本只有在代理執行時才會運行 — 留意它的動作，不要授予多餘權限。

技能和 MCP 伺服器或外掛有何不同？

MCP 伺服器或外掛為模型提供新工具 — 會執行並回傳結果的程式碼。技能提供的是知識與流程：如何處理任務、要遵循哪些步驟、好的成果長什麼樣子。它不需要伺服器或 API 金鑰。

總覽