Communitygithub.com

YouTube 行銷

建立、優化和管理 YouTube 內容,促進頻道成長、建立觀眾群並實現獲利。當有人要求「在 YouTube 上成長」、「優化 YouTube 影片」、「YouTube SEO」、「YouTube Shorts 策略」、「YouTube API 整合」、「自動化 YouTube 上傳」、「YouTube 分析」、「YouTube 縮圖」或「YouTube 內容策略」時使用。涵蓋長片、Shorts、SEO、縮圖設計、YouTube Data API、分析、獲利和成長策略。

YouTube 行銷 是什麼?

這個技能讓 AI 代理能夠創建高效的 YouTube 內容並與 YouTube Data API 整合。它詳細說明了 YouTube 的演算法與發現機制(搜尋與推薦),長片與 Shorts 的內容格式與規格,以及 YouTube SEO 的最佳實務(標題、描述、標籤、縮圖、字幕)。此外,它提供了透過 YouTube Data API v3 進行影片上傳、縮圖設定、播放清單管理的 TypeScript 程式碼範例,以及透過 YouTube Analytics API 查詢頻道統計資料和頂級影片的方法。技能也涵蓋了 YouTube 合作夥伴計畫(YPP)的獲利要求、收入來源,以及一個包含每週上傳節奏和上片後推廣策略的成長框架。它支援在 Claude Code、Cursor 等平台中,根據使用者的自然語言提示自動執行上傳、排程和分析任務。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/TerminalSkills/skills/tree/HEAD/skills/youtube-marketing

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

YouTube 行銷 是做什麼的?

概覽

此技能幫助 AI 代理創建高成效的 YouTube 內容並與 YouTube Data API 整合。涵蓋長片策略、Shorts、SEO 優化、縮圖設計、上傳自動化、分析、獲利路徑,以及針對 YouTube 搜尋與推薦演算法的成長策略。

操作說明

演算法與發現

搜尋(YouTube 是第二大搜尋引擎): 標題/描述/標籤關鍵字匹配、影片文字紀錄已建立索引、參與率(點擊率 + 觀看時間)、新內容加成。

推薦(佔 70% 以上觀看次數): 點擊率(縮圖 + 標題)、平均觀看時長、觀看時段、觀眾滿意度(按讚、分享、留言)、上傳頻率一致性。

什麼會扼殺觸及率:內容與標題不符的點擊誘餌、過長的開場白、不規律的上傳、誤導性的縮圖。

內容格式

長片(8-20 分鐘): 鉤子(0-30 秒)-> 背景說明(30 秒-1 分鐘)-> 主內容 -> 行動呼籲。規格:最低 1080p(偏好 4K)、MP4 H.264、清晰音訊 -14 至 -12 LUFS。留存技巧:每 30-60 秒模式中斷、開放式循環、章節/時間戳記、視覺多樣性。

Shorts(60 秒以下,9:16 直式): 前 1 秒內置入鉤子、單一聚焦的想法、適合循環的結尾、作為長片的漏斗。每週發布 3-5 部 Shorts。

社群貼文(500 位以上訂閱者): 投票、圖片、影片預告。兩次上傳之間每週發布 2-3 次。

YouTube SEO

標題: 60-70 個字元、主要關鍵字靠近開頭、數字 + 利益有效。公式:[主要關鍵字] — [利益/鉤子]([修飾詞])。範例:「Next.js 身份驗證 — 完整指南(2026)」

描述: 前 150 個字元會出現在搜尋結果中(前置關鍵字)。包含時間戳記/章節(至少 3 個)。總共 150-300 字。連結放在摺頁下方。

標籤: 每個影片 5-15 個、第一個是主要關鍵字、混合完全比對與較寬泛的詞彙。

縮圖: 1280x720px、高對比度、有表情的臉部、最多 3-5 個字粗體文字、一致的品牌風格、三分構圖法。

字幕: 上傳準確的 SRT(自動字幕有錯誤)。YouTube 會為搜尋而索引字幕文字。多語言字幕能擴大全球觸及範圍。

YouTube Data API v3

import { google } from 'googleapis';

const oauth2Client = new google.auth.OAuth2(
  process.env.GOOGLE_CLIENT_ID, process.env.GOOGLE_CLIENT_SECRET, process.env.GOOGLE_REDIRECT_URI
);
oauth2Client.setCredentials(tokens);
const youtube = google.youtube({ version: 'v3', auth: oauth2Client });

// 上傳影片
const res = await youtube.videos.insert({
  part: ['snippet', 'status'],
  requestBody: {
    snippet: {
      title: 'Next.js 身份驗證 — 完整指南(2026)',
      description: '學習如何在 Next.js 中實作身份驗證...\n\n0:00 簡介\n1:23 設定',
      tags: ['nextjs', '身份驗證', '教學'],
      categoryId: '28',
    },
    status: { privacyStatus: 'private', publishAt: '2026-03-01T15:00:00.000Z', selfDeclaredMadeForKids: false },
  },
  media: { body: fs.createReadStream('/path/to/video.mp4') },
});
await youtube.thumbnails.set({ videoId: res.data.id, media: { body: fs.createReadStream('/path/to/thumb.jpg') } });

// 上傳 Shorts(直式影片 + 標題含 #Shorts)
await youtube.videos.insert({
  part: ['snippet', 'status'],
  requestBody: {
    snippet: { title: '你不知道的 3 個 Git 指令 #Shorts', tags: ['shorts', 'git'], categoryId: '28' },
    status: { privacyStatus: 'public', selfDeclaredMadeForKids: false },
  },
  media: { body: fs.createReadStream('/path/to/short-vertical.mp4') },
});

// 建立播放清單並加入影片
const playlist = await youtube.playlists.insert({
  part: ['snippet', 'status'],
  requestBody: { snippet: { title: 'Next.js 完整課程' }, status: { privacyStatus: 'public' } },
});
await youtube.playlistItems.insert({
  part: ['snippet'],
  requestBody: { snippet: { playlistId: playlist.data.id, resourceId: { kind: 'youtube#video', videoId: 'abc123' } } },
});

分析

const youtubeAnalytics = google.youtubeAnalytics({ version: 'v2', auth: oauth2Client });

// 頻道統計資料
const stats = await youtubeAnalytics.reports.query({
  ids: 'channel==MINE', startDate: '2026-01-01', endDate: '2026-02-18',
  metrics: 'views,estimatedMinutesWatched,averageViewDuration,subscribersGained',
  dimensions: 'day', sort: '-day',
});

// 熱門影片
const top = await youtubeAnalytics.reports.query({
  ids: 'channel==MINE', startDate: '2026-01-01', endDate: '2026-02-18',
  metrics: 'views,estimatedMinutesWatched,averageViewDuration,likes',
  dimensions: 'video', sort: '-views', maxResults: 20,
});

獲利

YPP 要求: 1,000 位訂閱者 + 4,000 小時觀看時數(12 個月內)或 1,000 萬次 Shorts 觀看次數(90 天內)。

收入來源: 廣告收入(科技領域每千次曝光 $3-8 美元)、頻道會員、超級留言/感謝、YouTube 購物、Shorts 收入分成。

超越 YPP: 贊助(科技領域每千次觀看 $50-200 美元)、聯盟行銷、自有產品/課程、諮詢服務。

成長策略

每週上傳 1-2 部長片 + 3-5 部 Shorts。內容組合:50% 教學、25% Shorts、15% 跟蹤熱點、10% 社群互動。前 48 小時:到處分享、回覆每則留言、置頂一則提問留言、發布到相關社群。

範例

範例 1:優化並排程教學影片上傳

使用者提示:「將我的 Next.js 身份驗證教學影片上傳到 YouTube,包含適當的 SEO、自訂縮圖,並排程在週六下午 3 點 UTC 發布。」

代理將:

  1. 呼叫 youtube.videos.insert,設定 privacyStatus: 'private' 和 publishAt: '2026-03-07T15:00:00.000Z'
  2. 將標題設定為「Next.js 身份驗證 — 完整指南(2026)」,並將主要關鍵字置於開頭
  3. 撰寫一段 200 字的描述,包含時間戳記、關鍵字,並將資源連結放在摺頁下方
  4. 加入 10 個相關標籤,混合完全比對和較寬泛的詞彙
  5. 透過 youtube.thumbnails.set 上傳自訂縮圖

範例 2:分析頻道表現並找出成長機會

使用者提示:「提取我最近 30 天的 YouTube 分析資料,告訴我哪些影片帶來最多訂閱者,以及我的流量來自何處。」

代理將:

  1. 使用 dimensions: 'video' 和 metrics: 'subscribersGained,views,averageViewDuration' 查詢 youtubeAnalytics.reports,並按獲得訂閱者數排序
  2. 使用 dimensions: 'insightTrafficSourceType' 查詢流量來源,以識別搜尋、瀏覽、建議流量的比例
  3. 呈現前 5 部帶動訂閱的影片及其觀看時長和點擊率指標
  4. 根據哪些流量來源最強,建議內容策略調整

指導原則

  • 縮圖 + 標題決定了 80% 的點擊決定 — 花時間在上面
  • 前 30 秒決定觀眾是否留下 — 立即鉤住觀眾,不要冗長的開場
  • 先以不公開方式上傳、設定縮圖、加入結尾畫面,再發布(避免預設縮圖導致低點擊率)
  • 描述中的章節有助於提升留存率(觀眾會跳到相關部分,而不是離開)
  • 資訊卡和結尾畫面 — 永遠指向你表現最好的影片或相關播放清單
  • 上傳 SRT 字幕 — 自動字幕有錯誤,YouTube 會為搜尋而索引字幕文字
  • 持續性勝過病毒式傳播 — 每週 1 部影片持續兩年,勝過隨機發布
  • Shorts 和長片用途不同:Shorts 用於觸及,長片用於觀看時長和獲利
  • 研究「分析」的「觀眾」分頁,找出最佳發布時機
  • 每部影片都應該回答:「為什麼要點擊 THIS 影片,而不是關於這個主題的其他 10 部影片?」

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

TerminalSkills/skills

>- Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

TerminalSkills/skills

>- You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

TerminalSkills/skills

>- Generate short-form videos with AI — script writing, text-to-speech narration, stock footage selection, subtitle generation, and video assembly. Use when: creating TikTok/YouTube Shorts/Reels content, automating video production, building content pipelines.

TerminalSkills/skills

>- Animate 3D objects and characters in Blender with Python. Use when the user wants to keyframe properties, create armatures and rigs, set up IK/FK chains, animate shape keys for facial animation, edit F-Curves, use the NLA editor to blend actions, add drivers for expression-based animation, or script any animation workflow in Blender.

TerminalSkills/skills

>- Automate motion capture and tracking workflows in Blender with Python. Use when the user wants to import BVH or FBX mocap data, retarget motion to armatures, track camera or object motion from video, solve camera motion, clean up motion capture data, or script any tracking pipeline in Blender.

TerminalSkills/skills

>- You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

TerminalSkills/skills

>- Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

TerminalSkills/skills

>- Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.

TerminalSkills/skills

>- You are an expert in Chi, the lightweight, idiomatic Go HTTP router built on `net/http`. You help developers build composable HTTP services using Chi's middleware stack, route groups, URL parameters, sub-routers, and context-based request scoping — providing Express-like ergonomics while staying 100% compatible with Go's standard library.

TerminalSkills/skills

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

TerminalSkills/skills

>- Add live chat and customer support with Crisp. Use when a user asks to add a chat widget, implement live customer support, set up a help desk, create a knowledge base, or add a chatbot to a website.

TerminalSkills/skills

>- Assists with building custom interactive data visualizations using D3.js. Use when creating charts, graphs, maps, force layouts, or hierarchical diagrams that require fine-grained control beyond what charting libraries provide. Trigger words: d3, data visualization, chart, svg, scales, force graph, treemap, choropleth.

TerminalSkills/skills

dbt (data build tool) transforms data in your warehouse using SQL SELECT statements. Learn project setup, models, tests, documentation, incremental materializations, and integration with data warehouses like PostgreSQL, BigQuery, and Snowflake.

TerminalSkills/skills

>- You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines.

TerminalSkills/skills

Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, and run experiments with metric comparison. Works with any storage backend including S3, GCS, Azure, and local filesystems.

TerminalSkills/skills

>- You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give AI agents the ability to execute code, install packages, read/write files, and run long processes in isolated cloud environments — each sandbox is a lightweight VM that boots in ~150ms with full Linux, filesystem, and networking.

TerminalSkills/skills

>- Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

TerminalSkills/skills

>- Create advanced animations with GSAP. Use when building complex timelines, scroll-driven animations, SVG morphing, text animations, or high-performance web animations beyond CSS capabilities.

TerminalSkills/skills

>- Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the component catalog.

TerminalSkills/skills

When the user wants to perform load testing, stress testing, or performance testing of APIs and websites using k6. Also use when the user mentions "k6," "load test," "performance test," "stress test," "spike test," "soak test," "thresholds," "virtual users," or "VUs." For browser-based testing, see selenium.

相關技能