Back to Details

youtube-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

YouTube Research

YouTube调研

Three modes in one skill:
  1. Topic Research — competitive landscape, content gaps, strategic insights before planning a video
  2. Video Analysis — forensic deconstruction of transcripts to extract viral formulas and retention mechanics
  3. API Queries — direct YouTube Data API v3 access for search, stats, comments, and channel info
一个技能包含三种模式：
  1. 主题调研 —— 视频策划前梳理竞争格局、挖掘内容缺口、获取战略洞察
  2. 视频分析 —— 对字幕进行深度拆解，提取爆款公式和用户留存机制
  3. API 查询 —— 直接访问YouTube Data API v3，实现搜索、数据统计、评论获取、频道信息查询

When to Use

适用场景

  • Researching a video topic before planning production
  • Analyzing a competitor video to extract what makes it work
  • Fetching channel stats, video metrics, or comments via the API
  • Identifying content gaps and opportunities in a niche
  • 策划视频制作前调研主题
  • 分析竞品视频，总结其成功原因
  • 通过API获取频道统计数据、视频指标或评论
  • 挖掘垂直领域的内容缺口和机会

YouTube Data API Setup

YouTube Data API 配置

1. Get an API Key

1. 获取API Key

  1. Go to Google Cloud Console → APIs & Services → Library
  2. Enable YouTube Data API v3
  3. Create Credentials → API Key
bash
export YOUTUBE_API_KEY="your-api-key-here"
Important: When piping curl output, wrap the command in 
bash -c '...'
to preserve env vars:
bash
bash -c 'curl -s "https://..." -H "..." | jq .'
  1. 前往 Google Cloud Console → APIs & Services → 库
  2. 启用 YouTube Data API v3
  3. 创建凭据 → API Key
bash
export YOUTUBE_API_KEY="your-api-key-here"
重要提示： 当使用管道传输curl输出时，请将命令包裹在
bash -c '...'
中以保留环境变量：
bash
bash -c 'curl -s "https://..." -H "..." | jq .'

2. Key API Commands

2. 核心API命令

Search Videos:
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/search?part=snippet&q=YOUR_QUERY&type=video&maxResults=10&order=viewCount&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {videoId: .id.videoId, title: .snippet.title, channel: .snippet.channelTitle}'
Get Video Details (stats, duration):
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics,contentDetails&id=VIDEO_ID&key=${YOUTUBE_API_KEY}"' | jq '.items[0] | {title: .snippet.title, views: .statistics.viewCount, likes: .statistics.likeCount, duration: .contentDetails.duration}'
Get Channel by Handle:
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/channels?part=snippet,statistics&forHandle=@HANDLE&key=${YOUTUBE_API_KEY}"' | jq '.items[0] | {id: .id, title: .snippet.title, subscribers: .statistics.subscriberCount, videos: .statistics.videoCount}'
Get Video Comments:
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/commentThreads?part=snippet&videoId=VIDEO_ID&maxResults=20&order=relevance&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {author: .snippet.topLevelComment.snippet.authorDisplayName, text: .snippet.topLevelComment.snippet.textDisplay, likes: .snippet.topLevelComment.snippet.likeCount}'
Get Trending Videos:
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics&chart=mostPopular&regionCode=US&maxResults=10&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {title: .snippet.title, channel: .snippet.channelTitle, views: .statistics.viewCount}'
Quota: 10,000 units/day. Search = 100 units. Most others = 1 unit.
See YouTube Data API docs for full reference.
搜索视频：
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/search?part=snippet&q=YOUR_QUERY&type=video&maxResults=10&order=viewCount&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {videoId: .id.videoId, title: .snippet.title, channel: .snippet.channelTitle}'
获取视频详情（统计数据、时长）：
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics,contentDetails&id=VIDEO_ID&key=${YOUTUBE_API_KEY}"' | jq '.items[0] | {title: .snippet.title, views: .statistics.viewCount, likes: .statistics.likeCount, duration: .contentDetails.duration}'
根据Handle查询频道：
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/channels?part=snippet,statistics&forHandle=@HANDLE&key=${YOUTUBE_API_KEY}"' | jq '.items[0] | {id: .id, title: .snippet.title, subscribers: .statistics.subscriberCount, videos: .statistics.videoCount}'
获取视频评论：
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/commentThreads?part=snippet&videoId=VIDEO_ID&maxResults=20&order=relevance&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {author: .snippet.topLevelComment.snippet.authorDisplayName, text: .snippet.topLevelComment.snippet.textDisplay, likes: .snippet.topLevelComment.snippet.likeCount}'
获取热门视频：
bash
bash -c 'curl -s "https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics&chart=mostPopular&regionCode=US&maxResults=10&key=${YOUTUBE_API_KEY}"' | jq '.items[] | {title: .snippet.title, channel: .snippet.channelTitle, views: .statistics.viewCount}'
配额： 每天10,000个单位。搜索接口消耗100单位，其余多数接口消耗1单位。
完整参考请查看 YouTube Data API 文档。

Mode 1: Topic Research

模式1：主题调研

Conduct research before planning a new video. Focus on insights and big levers — not data dumping.
在策划新视频前开展调研，重点关注洞察和关键抓手，而非堆砌数据。

Workflow

工作流

Step 0: Create research file
Save all research to: 
./youtube/episode/[episode_number]_[topic_short_name]/research.md
If it already exists, read it and continue from where it left off.
Step 1: Understand the topic
  • What problem does this video solve?
  • Why would someone click on it?
  • What makes it relevant now?
Step 2: Research your own channel
Use the API to find related videos you've already published. Document:
  • Related videos (title, video ID, URL, key metrics)
  • What's already been covered and how to differentiate
Step 3: Competitor research
Search for 5–8 top videos on the topic. For each:
  • Get video details (views, likes, duration)
  • Note the title, angle, and what makes it successful
  • Synthesize common patterns and approaches
Step 4: Content gap analysis
Document:
  • What's saturated — 3–5 over-covered angles
  • Gaps (Opportunities) — rated ⭐⭐⭐ high / ⭐⭐ medium / ⭐ low
  • Recommended focus — specific angle + unique value proposition
Rating criteria:
  • ⭐⭐⭐ High: Significant gap, strong demand, clear differentiation
  • ⭐⭐ Medium: Moderate gap, some competition, good potential
  • ⭐ Low: Minor gap, heavily competed
步骤0：创建调研文件
将所有调研内容保存至：
./youtube/episode/[episode_number]_[topic_short_name]/research.md
如果文件已存在，读取文件并从上次中断的地方继续。
步骤1：理解主题
  • 这个视频解决什么问题？
  • 用户为什么会点击它？
  • 为什么它在当下有相关性？
步骤2：调研自有频道
使用API查找你已经发布的相关视频，记录：
  • 相关视频（标题、视频ID、URL、核心指标）
  • 已经覆盖过的内容，以及如何做出差异化
步骤3：竞品调研
搜索该主题下5–8个 top 视频，针对每个视频：
  • 获取视频详情（播放量、点赞数、时长）
  • 记录标题、切入角度、成功原因
  • 总结共性规律和常用方法
步骤4：内容缺口分析
记录：
  • 内容饱和区 —— 3–5个被过度覆盖的角度
  • 缺口（机会点） —— 按⭐⭐⭐ 高 / ⭐⭐ 中 / ⭐ 低评级
  • 推荐聚焦方向 —— 具体切入角度 + 独特价值主张
评级标准：
  • ⭐⭐⭐ 高：缺口显著、需求旺盛、差异化清晰
  • ⭐⭐ 中：存在中等缺口、有一定竞争、潜力不错
  • ⭐ 低：缺口很小、竞争激烈

Research File Template

调研文件模板

markdown
undefined
markdown
undefined

[Episode]: [Topic] - Research

[Episode]: [Topic] - Research

Episode Overview

Episode Overview

Topic: [Brief description] Target Audience: [Who this is for] Goal: [What viewers will learn/gain]
Topic: [Brief description] Target Audience: [Who this is for] Goal: [What viewers will learn/gain]

YouTube Research

YouTube Research

Your Previous Videos

Your Previous Videos

[Related videos with metrics]
[Related videos with metrics]

Top Competing Videos

Top Competing Videos

[5-8 videos: title, channel, views, angle, what works]
[5-8 videos: title, channel, views, angle, what works]

Key Insights

Key Insights

[Patterns and findings synthesized]
[Patterns and findings synthesized]

Content Gap Analysis

Content Gap Analysis

What's Already Well-Covered

What's Already Well-Covered

[List]
[List]

Content Gaps (Opportunities)

Content Gaps (Opportunities)

[Rated list with ⭐ ratings]
[Rated list with ⭐ ratings]

Recommended Focus

Recommended Focus

[Specific angle and unique value proposition]
[Specific angle and unique value proposition]

Production Notes

Production Notes

Status: Research Complete Created: [Date]
undefined
Status: Research Complete Created: [Date]
undefined

Subagents for Parallel Research

并行调研子代理

Use the 
Task
tool to run research tasks in parallel for faster results. Each task should have a focused, specific objective (e.g., "Search for top 8 videos on X and get their stats"). Synthesize findings after all tasks complete.
使用
Task
工具并行运行调研任务以提升效率。每个任务需要有明确具体的目标（例如"Search for top 8 videos on X and get their stats"）。所有任务完成后汇总结果。

Pitfalls

常见误区

  • Data dumping — Limit to 5–8 competitors, synthesize patterns instead of listing every video
  • Vague gaps — "Not much content on this" → identify the specific missing angle
  • Long reports — Focus on insights and big levers
Next step: Use 
youtube-content
skill to plan the video based on this research.
  • 堆砌数据 —— 仅调研5–8个竞品，总结规律而非罗列所有视频
  • 缺口描述模糊 —— 不要只说"Not much content on this"，要明确缺失的具体角度
  • 报告过长 —— 重点关注洞察和关键抓手
下一步： 基于本次调研结果，使用
youtube-content
技能策划视频。

Mode 2: Video Analysis

模式2：视频分析

Forensic deconstruction of video transcripts to extract viral formulas, hooks, and retention mechanics.
对视频字幕进行深度拆解，提取爆款公式、钩子设计和留存机制。

Getting the Transcript

获取字幕

Auto-fetch:
bash
python skills/youtube-research/scripts/fetch_transcript.py "YOUTUBE_URL_OR_VIDEO_ID"
Manual paste: YouTube's built-in transcript (click "..." → "Show transcript") or ytscribe.ai.
自动获取：
bash
python skills/youtube-research/scripts/fetch_transcript.py "YOUTUBE_URL_OR_VIDEO_ID"
手动粘贴： YouTube自带字幕（点击"..." → "Show transcript"）或ytscribe.ai。

Analysis Framework

分析框架

Approach the transcript like a crime scene — extract everything systematically. See 
reference/analysis-framework.md
for the full checklist and templates.
Analyze these 11 dimensions:
  1. Hook Architecture — Primary hook (first 3–8s), hook type, secondary hooks, fill-in-blank templates
  2. Structural Blueprint — Content framework (PAS, Story-Lesson-CTA, List-Depth-Summary), beat map, pacing
  3. Retention Mechanics — Open loops, pattern interrupts, curiosity gaps, payoff points
  4. Emotional Engineering — Emotional arc, trigger words, identity hooks, Us vs. Them dynamics
  5. Storytelling Elements — Narrative framework, character positioning, conflict/stakes, specificity
  6. Linguistic Patterns — Power phrases, sentence rhythm, repetition, conversational triggers
  7. Algorithm Signals — Watch time optimizers, engagement bait, share/save triggers
  8. CTA Architecture — Primary CTA, soft CTAs, timing, value exchange
  9. Viral Coefficient — Shareability score (1–10), comment bait density, crossover potential
  10. Reusable Templates — Fill-in-blank opening hooks (3 variations), section templates, transition library
  11. Implementation Playbook — Top 10 steal-this elements, niche adaptation, A/B test suggestions
把字幕当作犯罪现场一样分析，系统提取所有信息。完整检查清单和模板请查看
reference/analysis-framework.md
。
从以下11个维度分析：
  1. 钩子架构 —— 主钩子（前3–8秒）、钩子类型、次级钩子、填空模板
  2. 结构蓝图 —— 内容框架（PAS、Story-Lesson-CTA、List-Depth-Summary）、节奏节点、内容 pacing
  3. 留存机制 —— 开放式循环、模式打断、好奇心缺口、回报节点
  4. 情绪设计 —— 情绪曲线、触发词、身份钩子、Us vs. Them 对立设计
  5. 讲故事要素 —— 叙事框架、角色定位、冲突/利害关系、具体细节
  6. 语言模式 —— 有力表达、句子节奏、重复、对话式触发点
  7. 算法信号 —— 观看时长优化手段、引导互动设计、引导分享/收藏的触发点
  8. CTA架构 —— 主CTA、软CTA、时间点设置、价值交换
  9. 爆款系数 —— 可分享性评分（1–10）、引导评论密度、破圈潜力
  10. 可复用模板 —— 填空式开场钩子（3种变体）、章节模板、转场库
  11. 落地执行手册 —— 前10个可直接复用的元素、垂直领域适配、A/B测试建议

Before Analysis, Collect Context

分析前收集背景信息

  • Your niche/topic
  • Your content style (casual, educational, hype, etc.)
  • Target platform and video length goal
  • 你的垂直领域/主题
  • 你的内容风格（休闲、科普、亢奋等）
  • 目标平台和视频时长目标

Output Format

输出格式

Structure output with all 11 sections. End with a Quick Reference Cheatsheet — one-page summary of all extracted patterns for rapid implementation.
输出结构需包含全部11个模块，最后附上快速参考速查表 —— 一页纸汇总所有提取的规律，方便快速落地。

Tools

工具

  • YouTube API: 
    bash -c 'curl ...'
    with 
    $YOUTUBE_API_KEY
  • MCP (if available): 
    mcp__plugin_yt-content-strategist_youtube-analytics__search_videos
    , 
    get_video_details
    , 
    get_channel_details
  • Web: 
    WebSearch
    and 
    WebFetch
    for industry trends and context
  • YouTube API: 配合
    $YOUTUBE_API_KEY
    使用
    bash -c 'curl ...'
  • MCP（如果可用）: 
    mcp__plugin_yt-content-strategist_youtube-analytics__search_videos
    , 
    get_video_details
    , 
    get_channel_details
  • 网页工具: 用
    WebSearch
    和
    WebFetch
    查询行业趋势和背景信息