Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

youtube-scriptwritingYouTube 剧本创作

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

1,384

周安装

56

GitHub Stars

9

下载量

435
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:youtube-scriptwriting(YouTube 剧本创作)
来源仓库:https://github.com/cdeistopened/skill-stack
仓库路径:skills/youtube-scriptwriting
安装命令:
npx skills add https://github.com/cdeistopened/skill-stack --skill youtube-scriptwriting
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/cdeistopened/skill-stack --skill youtube-scriptwriting

简介

协助撰写 YouTube 视频配套文案与说明文档。

  • 适合内容团队统一术语、完善章节结构。
  • 通过 npx skills add 命令从仓库安装。
  • 应避免过度营销表述,保持客观中立。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • youtube-scriptwriting 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

YouTube Script Writing

Transform disorganized ideas into retention-optimized scripts through a checkpoint-based workflow.

Core Psychology

All great scripts operate on one principle: Reality must beat expectations.

  • Viewer expectations = what they think will happen based on title/thumbnail
  • Reality = what you actually deliver in the video
  • When reality > expectations → satisfaction, engagement, shares
  • When reality < expectations → disappointment, drop-off, bounce

Every decision in scriptwriting serves this gap.

The Workflow

Work through these checkpoints in order. Each builds on the previous.

Checkpoint 1: Define the Foundation

Before writing anything:

  1. Target audience: Who specifically is watching? What do they already know?
  2. Desired emotion: Pick ONE primary emotion to transfer:

- Awe/inspiration - Amusement/humor - Excitement/joy - Anger/outrage - Surprise/shock/curiosity - Sadness/empathy

  1. Core promise: One sentence describing what viewer gets from watching

Checkpoint 2: Research & Mine for Shock

Find the facts that will beat expectations. See references/research.md.

Shock Score Method: Rate each fact 1-100 based on "How many viewers would NOT know this?"

  • 80+ = Gold (most viewers surprised)
  • 50-79 = Good supporting points
  • Below 50 = Skip unless essential context

Collect 5-10 high-shock facts before proceeding.

Checkpoint 3: Write the Hook

The hook confirms the click and opens a curiosity loop. See references/hooks.md for the 9 proven formats.

Quick Formula (works for any niche):

  • Target: Who is this for?
  • Transformation: What will they gain?
  • Stakes: What happens if they don't watch?

Hook Commandments (verify all 4):

  1. Alignment: Visual, spoken, and text hooks match
  2. Speed: Value promised in first 3 seconds
  3. Clarity: Topic is unmistakable
  4. Curiosity: Opens a question they must answer

Checkpoint 4: Choose Story Structure & Outline

Pick ONE structure that fits your content. See references/structures.md for all 7 formats.

Most Common Structures:

  • Tutorial: Step-by-step process → Hook → Steps → Outro
  • Listicle: Ordered items → Hook → List → Outro
  • Problem-Solver: Pain → Solution → Hook → Problem → Solution → Outro
  • Case Study: How X achieved Y → Hook → Framework → Outro

Create a bullet outline BEFORE writing. Sequence your shock facts logically.

Checkpoint 5: Write the Body

For each section, use the Value Loop:

  1. Context: What is it? (Simple, clear)
  2. Application: How to use it? (Examples)
  3. Framing: Why does it matter? (Connect to bigger picture)

Retention Techniques (see references/retention.md):

  • Rehooks: Every 30-60 seconds, reagitate the promise ("But here's where it gets interesting...")
  • Setups & Payoffs: Tease information, delay reveal, then deliver
  • Second-best first: Put your second-best point first, best point second (creates ascending pattern)

Checkpoint 6: Edit for Quality

Run three audits on your draft. See references/editing.md.

1. Story Flow Audit

  • Read each line: Is this necessary or a tangent?
  • Delete anything that breaks the through-line
  • Test: Can viewer follow beginning to end without getting lost?

2. Comprehension Audit

  • Target 6th grade vocabulary
  • Shorter sentences (staccato, not run-on)
  • Active voice ("The dog jumped" not "The jumping was done by the dog")
  • Restate complex ideas twice, second time simpler

3. Speed-to-Value Audit

  • Is value signaled in first 3 seconds?
  • Rehooks every 30-60 seconds?
  • Outro summarizes or extends value?

Checkpoint 7: Outro & CTA

Binge Loop Formula (last 15-30 seconds):

  1. Link back to video content naturally
  2. Introduce a NEW problem/question
  3. Promise to solve it in another video or resource

Quick Reference: Script Template

HOOK (0-15 seconds)
- Confirm the click
- Open curiosity loop
- Establish credibility (optional)

BODY SECTION 1 (Rehook → Content → Payoff)
[Second-best point]

BODY SECTION 2 (Rehook → Content → Payoff)
[Best point]

BODY SECTION 3+ (Rehook → Content → Payoff)
[Remaining points in descending order]

OUTRO (Last 15-30 seconds)
- Summarize value delivered
- Binge loop to next video/resource

When to Use Each Reference

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.92%
按下载量换算165

Claude

30.3%
按下载量换算132

Cursor

19.66%
按下载量换算86

Gemini CLI

8.94%
按下载量换算39

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills