plan-video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Plan Video

视频策划方案

Overview

概述

This orchestrator sequences foundation skills to produce a complete video plan: researched titles, thumbnail concepts, hook strategies, and a content outline. It manages the user selection workflow between steps but delegates all content generation to specialized skills.
Core Principle: This is a thin orchestrator. Never generate titles, thumbnails, hooks, or outlines manually. Always delegate to the appropriate foundation skill.
该协调器编排基础技能以生成完整的视频策划方案,包括经过调研的标题、缩略图概念、钩子策略以及内容大纲。它负责管理各步骤之间的用户选择工作流,但将所有内容生成任务委托给专业技能。
核心原则:这是一个轻量协调器。绝不要手动生成标题、缩略图、钩子或大纲。始终将任务委托给对应的基础技能。

YouTube-Specific Context

YouTube专属上下文

Episode Directory Convention

剧集目录规范

All episode files live under
./youtube/episode/[episode_number]_[topic_short_name]/
.
  • Research file:
    research.md
    in the episode directory
  • Plan file:
    plan.md
    in the episode directory
  • Thumbnails: saved to the episode directory during finalization
所有剧集文件都存储在
./youtube/episode/[episode_number]_[topic_short_name]/
路径下。
  • 调研文件:剧集目录下的
    research.md
  • 策划文件:剧集目录下的
    plan.md
  • 缩略图:在最终定稿阶段保存到剧集目录

Channel Information

频道信息

If a local channel context file exists (e.g.,
./youtube/channel.md
or similar), load it at the start of the workflow to provide channel-specific context to downstream skills.
如果存在本地频道上下文文件(例如
./youtube/channel.md
或类似文件),请在工作流开始时加载它,以便为下游技能提供频道专属上下文。

YouTube MCP Tools Available

可用的YouTube MCP工具

When
content-strategy:research
is invoked from this orchestrator, the YouTube Analytics MCP tools are available for data gathering. These tools provide access to:
  • search_videos
    -- find videos by keyword, channel, or criteria
  • get_video_details
    -- video stats, views, likes, comments, publish date
  • get_channel_details
    -- channel metadata, subscriber count, video count
  • get_video_comments
    -- comment text and sentiment data
  • get_video_transcript
    -- full video transcript
  • get_related_videos
    -- videos related to a specific video
  • get_trending_videos
    -- currently trending videos
  • get_video_enhanced_transcript
    -- enhanced transcript with timestamps
The YouTube Researcher agent (defined in this plugin's
agents/youtube-researcher.md
) can also be used for structured data gathering tasks.
当从该协调器调用
content-strategy:research
时,可使用YouTube Analytics MCP工具进行数据收集。这些工具支持:
  • search_videos
    -- 按关键词、频道或条件查找视频
  • get_video_details
    -- 视频统计数据、观看量、点赞数、评论数、发布日期
  • get_channel_details
    -- 频道元数据、订阅人数、视频数量
  • get_video_comments
    -- 评论文本和情感数据
  • get_video_transcript
    -- 完整视频字幕
  • get_related_videos
    -- 与特定视频相关的视频
  • get_trending_videos
    -- 当前热门视频
  • get_video_enhanced_transcript
    -- 带时间戳的增强版字幕
YouTube Researcher agent(在该插件的
agents/youtube-researcher.md
中定义)也可用于结构化数据收集任务。

When to Use

使用场景

Use this skill when:
  • Research has been completed and you need to create a video plan
  • The user asks to plan a new video
  • You need title, thumbnail, hook, and outline options for a video
  • You want to produce a production-ready plan with multiple options for user selection
在以下场景中使用本技能:
  • 调研已完成,需要创建视频策划方案时
  • 用户要求策划新视频时
  • 需要为视频提供标题、缩略图、钩子和大纲选项时
  • 想要生成可供用户选择多个选项的可落地策划方案时

Prerequisites

前置条件

MANDATORY: Research for the video must be completed first. Either:
  1. Research file exists at
    ./youtube/episode/[episode_number]_[topic_short_name]/research.md
    , OR
  2. Invoke
    content-strategy:research
    to conduct research first (YouTube MCP tools are available)
强制要求:必须先完成视频调研。满足以下任一条件即可:
  1. 调研文件已存在于
    ./youtube/episode/[episode_number]_[topic_short_name]/research.md
    ,或者
  2. 先调用
    content-strategy:research
    进行调研(可使用YouTube MCP工具)

Planning Workflow

策划工作流

Execute all steps below in order. Track progress systematically.
按顺序执行以下所有步骤,系统地跟踪进度。

Step 0: Load Research

步骤0:加载调研数据

Read the research file for this episode:
  • Location:
    ./youtube/episode/[episode_number]_[topic_short_name]/research.md
If research does not exist, invoke
content-strategy:research
first. The YouTube MCP tools are available from this orchestrator context, enabling the research skill to gather YouTube-specific data.
The video plan MUST incorporate research findings at each step.
读取本剧集的调研文件:
  • 路径:
    ./youtube/episode/[episode_number]_[topic_short_name]/research.md
如果调研文件不存在,请先调用
content-strategy:research
。从该协调器上下文可访问YouTube MCP工具,使调研技能能够收集YouTube专属数据。
视频策划方案必须在每个步骤中融入调研结果。

Step 1: Create Plan File

步骤1:创建策划文件

Create a new plan file at:
./youtube/episode/[episode_number]_[topic_short_name]/plan.md
If a plan file already exists, read it to understand what has been done so far and continue from there.
Initialize the plan file with this template:
markdown
undefined
在以下路径创建新的策划文件:
./youtube/episode/[episode_number]_[topic_short_name]/plan.md
如果策划文件已存在,请读取它以了解已完成的工作,并从当前进度继续。
使用以下模板初始化策划文件:
markdown
undefined

[Episode_Number]: [Topic] - Video Plan

[Episode_Number]: [Topic] - 视频策划方案

Research Summary

调研摘要

[Summary of research insights]
[调研洞察摘要]

Titles

标题

[3 title options with rationale and star ratings]
[3个标题选项,附理由和星级评分]

Thumbnails

缩略图

[2 thumbnail concepts per title with rationale and star ratings]
[每个标题对应2个缩略图概念,附理由和星级评分]

Hooks

钩子

[3 hook options for selected title+thumbnail with rationale and star ratings]
[为选定的标题+缩略图提供3个钩子选项,附理由和星级评分]

High-Level Content Outline

高层级内容大纲

[Section structure with key points]
[分段结构及关键点]

Final Plan

最终策划方案

[Selected title, 3 AB test thumbnails, selected hook, outline]

Update this document as you progress through the planning steps.
[选定的标题、3个AB测试缩略图、选定的钩子、大纲]

在执行策划步骤的过程中更新此文档。

Step 2: Generate Title Options

步骤2:生成标题选项

  1. MANDATORY: Invoke
    content-strategy:title
    to generate 3 optimized titles.
    • The skill will automatically load
      references/youtube-title-formulas.md
      for proven title patterns.
    • Provide the research summary as context.
  2. Document all title options in the plan file including:
    • Title text
    • Rationale for why it is predicted to perform well and how it aligns with research insights
    • Star rating from 1-3 stars indicating your recommendation
NOTE: You MUST complete title generation before proceeding to thumbnails, as thumbnails need to complement the titles.
  1. 强制要求:调用
    content-strategy:title
    生成3个优化后的标题。
    • 该技能会自动加载
      references/youtube-title-formulas.md
      中的成熟标题模板。
    • 提供调研摘要作为上下文。
  2. 在策划文件中记录所有标题选项,包括:
    • 标题文本
    • 预测其表现良好的理由,以及如何与调研洞察对齐
    • 1-3星的星级评分(表示你的推荐程度)
注意:必须先完成标题生成,再进行缩略图制作,因为缩略图需要与标题互补。

Step 3: Generate Thumbnail Concepts

步骤3:生成缩略图概念

  1. MANDATORY: Invoke
    visual-design:thumbnail
    to generate 2 thumbnail concepts for each title. These should be concept descriptions only, not actual images yet.
    • The skill will automatically load
      references/thumbnail-formulas.md
      for proven thumbnail patterns.
    • Provide each title as context so thumbnails complement them.
  2. Document all thumbnail concepts in the plan file including:
    • Title pairing
    • Concept description
    • Rationale for why it is predicted to perform well, how it aligns with research, and how it complements the title
    • Star rating for top 3 thumbnail concepts
  1. 强制要求:调用
    visual-design:thumbnail
    为每个标题生成2个缩略图概念。这些仅为概念描述,而非实际图片。
    • 该技能会自动加载
      references/thumbnail-formulas.md
      中的成熟缩略图模板。
    • 提供每个标题作为上下文,使缩略图与标题互补。
  2. 在策划文件中记录所有缩略图概念,包括:
    • 对应的标题
    • 概念描述
    • 预测其表现良好的理由、如何与调研对齐,以及如何与标题互补
    • 排名前三的缩略图概念的星级评分

Step 4: Present Recommendation and Get User Selection

步骤4:呈现推荐方案并获取用户选择

  1. Present all title/thumbnail combinations to the user, along with your top 3 recommended title + thumbnail pairings.
  2. Ask the user to select their one preferred title + thumbnail pairing to proceed with.
  3. Update both the title and thumbnail sections in the plan file to indicate the user's selection with a (User Selection) marker next to the selected options.
CRITICAL: Present ALL options so the user can make an informed decision. Do not simply select one option and tell the user to use it.
  1. 向用户展示所有标题/缩略图组合,以及你推荐的3个最佳标题+缩略图组合。
  2. 请求用户选择一个偏好的标题+缩略图组合以继续。
  3. 在策划文件的标题和缩略图部分更新,在用户选定的选项旁标记(用户选定)。
关键:展示所有选项,以便用户做出明智的决定。不要只选择一个选项并告知用户使用它。

Step 5: Generate Hook Strategy

步骤5:生成钩子策略

  1. MANDATORY: Invoke
    content-strategy:hook
    to generate 3 retention-optimized hooks, only for the user's selected title + thumbnail pairing.
    • The skill will automatically load
      references/youtube-hooks.md
      for proven hook patterns.
    • Provide the selected title + thumbnail concept as context.
  2. Document all hook strategies in the plan file including:
    • Hook strategy description (including the actual hook script)
    • Rationale for why it is predicted to perform well, how it aligns with research, and how it complements the title + thumbnail
    • Star rating for each hook
  3. Present all hook options to the user and ask the user to select their preferred hook strategy.
  4. Update the hook section in the plan file to indicate the user's selection.
The plan should now contain a user-selected title, thumbnail, and hook combination.
  1. 强制要求:仅针对用户选定的标题+缩略图组合,调用
    content-strategy:hook
    生成3个优化留存率的钩子。
    • 该技能会自动加载
      references/youtube-hooks.md
      中的成熟钩子模板。
    • 提供选定的标题+缩略图概念作为上下文。
  2. 在策划文件中记录所有钩子策略,包括:
    • 钩子策略描述(包含实际钩子脚本)
    • 预测其表现良好的理由、如何与调研对齐,以及如何与标题+缩略图互补
    • 每个钩子的星级评分
  3. 向用户展示所有钩子选项,并请求用户选择偏好的钩子策略。
  4. 在策划文件的钩子部分更新,标记用户的选定项。
此时,策划方案应包含用户选定的标题、缩略图和钩子组合。

Step 6: High-Level Content Outline

步骤6:高层级内容大纲

  1. MANDATORY: Invoke
    writing:copywriting
    to create a high-level content outline.
    • The skill will automatically load
      references/youtube-script.md
      for proven script structure patterns.
    • Provide the selected title, thumbnail concept, and hook as context.
  2. Create and document the strategic roadmap:
    • Break video into sections (Hook, Intro, Main Content, Outro)
    • List key points and estimated durations
    • Identify critical demonstrations/examples
    • Note transitions
  3. Keep the outline VERY HIGH-LEVEL. Structure and key points only, no detailed scripts. Do not assume specific content that should be covered -- leave that to the content creator. Focus on what is important to cover from the viewer's perspective.
  1. 强制要求:调用
    writing:copywriting
    创建高层级内容大纲。
    • 该技能会自动加载
      references/youtube-script.md
      中的成熟脚本结构模板。
    • 提供选定的标题、缩略图概念和钩子作为上下文。
  2. 创建并记录战略路线图:
    • 将视频分为多个部分(钩子、引言、主要内容、结尾)
    • 列出关键点和预估时长
    • 确定关键演示/示例
    • 标注过渡环节
  3. 大纲必须保持极高的层级。仅包含结构和关键点,不要写详细脚本。不要假设应涵盖的具体内容——留给内容创作者处理。重点从观众的角度出发,确定需要涵盖的重要内容。

Step 7: Finalize Plan with AB Testing Thumbnails

步骤7:生成AB测试缩略图以定稿策划方案

Now that the user has selected their preferred title, thumbnail, and hook, finalize the plan.
  1. MANDATORY: Invoke
    visual-design:thumbnail
    to generate 3 thumbnail options for AB testing. These should be actual images generated with
    thumbkit
    , not just concepts. The first thumbnail should be based on the user's selected thumbnail concept. The other 2 should test different visual styles of the first thumbnail.
  2. Update the final plan section in the plan file with the complete final selections:
markdown
undefined
用户已选定偏好的标题、缩略图和钩子后,即可定稿策划方案。
  1. 强制要求:调用
    visual-design:thumbnail
    生成3个用于AB测试的缩略图。这些应是使用
    thumbkit
    生成的实际图片,而非仅概念。第一个缩略图基于用户选定的缩略图概念,另外两个则测试该缩略图的不同视觉风格。
  2. 在策划文件的最终策划方案部分更新完整的最终选择:
markdown
undefined

Final Plan

最终策划方案

  • Title: [Selected title]
  • Thumbnails:
    • Thumbnail A Thumbnail A Description
    • Thumbnail B Thumbnail B Description
    • Thumbnail C Thumbnail C Description
  • Hook: [Selected hook strategy]
  • Rationale: [Why this combination works]

A final selection should **ALWAYS** have 3 thumbnails to test.
  • 标题:[选定的标题]
  • 缩略图:
    • 缩略图A 缩略图A描述
    • 缩略图B 缩略图B描述
    • 缩略图C 缩略图C描述
  • 钩子:[选定的钩子策略]
  • 理由:[该组合有效的原因]

最终选择**必须**包含3个用于测试的缩略图。

Execution Guidelines

执行准则

Always Invoke Foundation Skills

始终调用基础技能

NEVER generate titles, thumbnails, hooks, or outlines manually. Always invoke:
  • content-strategy:title
    for title generation
  • visual-design:thumbnail
    for thumbnail concepts and images
  • content-strategy:hook
    for hook strategies
  • writing:copywriting
    for content outline
绝不要手动生成标题、缩略图、钩子或大纲。始终调用:
  • content-strategy:title
    生成标题
  • visual-design:thumbnail
    生成缩略图概念和图片
  • content-strategy:hook
    生成钩子策略
  • writing:copywriting
    生成内容大纲

Provide Multiple Options

提供多个选项

CRITICAL: Always include ALL options so the user can make an informed decision. Do not simply select one option and tell the user to use it.
关键:始终提供所有选项,以便用户做出明智的决定。不要只选择一个选项并告知用户使用它。

Ensure Complementarity

确保互补性

Verify that title/thumbnail/hook work together:
  • Thumbnail complements title visually
  • Hook extends curiosity (does not repeat title)
  • All elements align with the unique value proposition
验证标题/缩略图/钩子是否协同工作:
  • 缩略图在视觉上与标题互补
  • 钩子增强好奇心(不重复标题内容)
  • 所有元素与独特价值主张对齐

Back Recommendations with Research

用调研结果支持推荐

When recommending combinations:
  • Reference content gaps from research
  • Cite competitor insights
  • Explain how the combination addresses the opportunity
在推荐组合时:
  • 引用调研中发现的内容空白
  • 提及竞品洞察
  • 解释该组合如何抓住机会

Quality Checklist

质量检查清单

Verify completion before finalizing plan:
  • Research file loaded and reviewed
  • content-strategy:title
    invoked -- 3 title options generated
  • visual-design:thumbnail
    invoked -- 2 thumbnail concepts per title
  • User selected title + thumbnail pairing
  • content-strategy:hook
    invoked -- 3 hook strategies generated
  • User selected hook strategy
  • writing:copywriting
    invoked -- high-level content outline created
  • visual-design:thumbnail
    invoked -- 3 AB testing thumbnails generated
  • Plan file complete with all sections populated
  • Recommendations marked by star rating
  • Title/thumbnail/hook complementarity verified
  • Recommendations backed by research insights
在定稿策划方案前验证是否完成以下项:
  • 已加载并审阅调研文件
  • 已调用
    content-strategy:title
    -- 生成3个标题选项
  • 已调用
    visual-design:thumbnail
    -- 每个标题对应2个缩略图概念
  • 用户已选定标题+缩略图组合
  • 已调用
    content-strategy:hook
    -- 生成3个钩子策略
  • 用户已选定钩子策略
  • 已调用
    writing:copywriting
    -- 创建高层级内容大纲
  • 已调用
    visual-design:thumbnail
    -- 生成3个AB测试缩略图
  • 策划文件所有部分已填充完整
  • 推荐方案已标记星级评分
  • 已验证标题/缩略图/钩子的互补性
  • 推荐方案已用调研洞察支持

Common Pitfalls to Avoid

需避免的常见误区

  1. Skipping Skill Invocation: Generating titles/thumbnails/hooks manually -- must invoke foundation skills
  2. Single Option: Only providing one recommendation -- provide all options to the user along with your recommendations
  3. Missing Research: Starting without research -- load research or invoke research skill first
  4. Ignoring Complementarity: Title/thumbnail/hook don't work together -- verify alignment
  5. No Rationale: Recommendations without explanation -- back with research insights
  6. Too-Detailed Outline: Writing a full script instead of high-level structure -- keep it strategic
  1. 跳过技能调用:手动生成标题/缩略图/钩子 -- 必须调用基础技能
  2. 单一选项:仅提供一个推荐方案 -- 向用户提供所有选项及你的推荐
  3. 缺少调研:未进行调研就开始 -- 先加载调研或调用调研技能
  4. 忽视互补性:标题/缩略图/钩子不协同工作 -- 验证对齐情况
  5. 无理由说明:推荐方案未附解释 -- 用调研洞察支持
  6. 大纲过于详细:编写完整脚本而非高层级结构 -- 保持策略性

Example Execution

执行示例

Scenario: User requests plan for video about "Building AI agents with memory" (research already complete)
  1. Load research -- Read
    ./youtube/episode/18_ai_agents_with_memory/research.md
    , extract key insights
  2. Create plan file at
    ./youtube/episode/18_ai_agents_with_memory/plan.md
  3. Invoke
    content-strategy:title
    -- 3 title options focused on practical implementation
  4. Invoke
    visual-design:thumbnail
    -- 2 concepts per title (6 total)
  5. Present all options, user selects title + thumbnail pairing
  6. Invoke
    content-strategy:hook
    -- 3 hook strategies for selected pairing
  7. User selects hook
  8. Invoke
    writing:copywriting
    -- high-level content outline
  9. Invoke
    visual-design:thumbnail
    -- 3 AB testing thumbnails for final plan
  10. Update plan file with complete final selections
Result: Production-ready plan with multiple options for user selection, all backed by research and generated using proven patterns from foundation skills.
场景:用户要求为“构建带记忆的AI Agent”主题的视频制定策划方案(调研已完成)
  1. 加载调研 -- 读取
    ./youtube/episode/18_ai_agents_with_memory/research.md
    ,提取关键洞察
  2. ./youtube/episode/18_ai_agents_with_memory/plan.md
    路径下创建策划文件
  3. 调用
    content-strategy:title
    -- 生成3个聚焦实操的标题选项
  4. 调用
    visual-design:thumbnail
    -- 每个标题对应2个概念(共6个)
  5. 展示所有选项,用户选定标题+缩略图组合
  6. 调用
    content-strategy:hook
    -- 为选定组合生成3个钩子策略
  7. 用户选定钩子
  8. 调用
    writing:copywriting
    -- 创建高层级内容大纲
  9. 调用
    visual-design:thumbnail
    -- 生成3个用于AB测试的缩略图
  10. 更新策划文件,填充完整的最终选择
结果:生成可落地的策划方案,包含多个供用户选择的选项,所有内容均基于调研并使用基础技能中的成熟模板生成。