Communitygithub.com

YouTube Copy - YouTube 元数据生成

根据用户提供的视频脚本、主题或 PR,生成包括标题、描述、标签和时间戳章节在内的完整 YouTube 元数据。

YouTube Copy - YouTube 元数据生成 是什么?

该技能专为需要高效、专业地制作 YouTube 视频元数据的 AI 代理用户设计。它能够根据转录文本(最好是带时间戳的 SRT 格式)、主题描述或自由格式输入,自动生成四项关键元数据:点击率高的标题、SEO 优化的描述、相关标签以及视频章节。标题生成遵循业界最佳实践(如 vidIQ 的 11 种公式),注重关键词前置、长度控制(60-70字符)和情感唤起。描述则采用“钩子-扩展-章节-标签”的结构化写法,确保首页折叠区即展示核心信息。标签系统支持 5-15 个覆盖宽泛与具体关键词的标签,以提升可发现性。章节生成要求输入必须带时间戳,且严格遵循 YouTube 官方规则(首章 00:00,至少 3 章,每章 ≥10 秒)。该技能可以独立使用,也可被 `/produce-video` 工作流调用,最终产出标准的 `youtube.md` 文件。一个重要的硬性规则是:全文禁止使用长破折号(— 或 –),一律用短横线 `-` 代替。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/AlemTuzlak/skills/tree/HEAD/skills/youtube-copy

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

YouTube Copy

编写驱动点击和排名的四部分 YouTube 元数据:标题、描述、标签、章节。所有内容必须以提供的素材(脚本/主题)为基础——切勿编造素材未支持的说法。对于章节,你需要一个带时间戳的素材(SRT 或 words.json);如果没有时间戳,则向用户索取,或跳过章节。

输出格式

按照以下格式编写 youtube.md(或打印相同结构):

# YouTube

**标题**

<title>

**描述**

<description>

**标签**

#tag1 #tag2 #tag3 ...

**章节**

00:00 - <chapter>
01:15 - <chapter>
...

(当 /produce-video 调用此技能时,将 youtube.md 写入输出文件夹。)

编写规则(不可协商)

永远不要使用长破折号(— 或 –)。请改用短横线 -。 此规则适用于标题、描述、章节分隔符等所有内容。

标题(最具杠杆作用的元素)

  • 60-70 个字符(硬性上限 100;超过约 70 个字符会在大多数平台上截断)。
  • 主要关键词尽量靠前,以便 YouTube 和观众立即了解主题。
  • 做到以下三点:激发好奇/情感(惊喜、紧迫感、FOMO、利益)、包含关键词、设定诚实的预期(过度宣传的标题会损害观看时长,属于标题党——请避免)。
  • 在自然合理的情况下使用数字(数字吸引眼球)以及情感/强力词汇(如“actually”、“finally”、“stop”、“the right way”、“type-safe”、“without”)。
  • 使用受众真实的行话,而非泛泛的措辞。
  • 可选:仅当能增加发现度时,可在标题中加入 1-2 个相关话题标签;通常建议标题中省略。
  • 避免:误导性诱饵、全部大写的垃圾信息、粗俗语言、超过 70 个字符。
  • 有用的公式起点(选择适合的,不必强求):“How to X (without Y)”、“The X that Y”、“Stop doing X - do this instead”、“X explained in N minutes”、“I tried X so you don't have to”、“N ways to X”。

描述

结构化的、前置加载的描述(前约 100-160 个字符显示在折叠区上方/搜索结果中):

  1. 钩子(前 1-2 句),包含主要关键词——回答“这是什么以及为什么要看?”。承诺结果。
  2. 一个简短段落(2-4 句),扩展观众能学到什么。
  3. 章节/时间戳(见下文):适用于视频超过约 10 分钟时(或存在明确分段时)。
  4. 可选链接/行动号召(主要链接、“接下来观看”、订阅)——仅在用户提供时才使用;不要编造 URL。
  5. 末尾输入 2-3 个相关话题标签。
  • 长度:紧凑且有用,大约 150-300 个单词 / 不超过约 1000 个字符。为人类而写;自然融入相关关键词,切勿堆砌关键词。

标签

  • 5-15 个标签,每个标签内可以包含空格(多个单词的标签中不要求去除空格,但请保持整洁)。
  • 主要关键词/短语在前,然后混合宽泛标签(例如 react、webdev)和具体标签(例如 react router loader data、unstable_useRouteLoaderData)。
  • 质量重于数量;所有标签必须真实描述内容。不要使用无关/垃圾标签,也不要使用竞争对手名称。
  • 输出时在 youtube.md 中为每个标签添加 # 前缀以提高可读性(它们在 YouTube 的标签框中输入时不带 #)。

章节(需要带时间戳的素材)

YouTube 的硬性规则:第一章必须是 00:00,至少 3 个章节且按升序排列,每个章节长度 ≥ 10 秒。

  • **第一章(00:00)**回答“他们为什么点击?”——命名该节的价值点/主题(例如“类型安全的加载器数据”、“最终结果”),而不是“介绍”。
  • 标题:3-8 个单词,一个清晰的名词短语(移动端会截断长标题)。用该节的实际主题替换无用标签(“介绍”、“演示”、“结论”、“问答”)。
  • 频率:教程类大约每 2-4 分钟一个章节,长篇内容每 5-10 分钟一个章节;总计 5-15 个章节,切勿超过约 20 个。
  • 每个 MM:SS 起始时间从带时间戳的素材中推导(该节实际开始的时间点)。使用 MM:SS(超过一小时则用 H:MM:SS)。分隔符为 -(短横线),绝不能用长破折号。

流程

  1. 读取素材。如果是 SRT/words.json,使用时间戳生成章节;如果是纯文本或主题,则编写标题/描述/标签,并注明章节需要带时间戳的素材。
  2. 确定主要关键词/主题(用户会搜索的内容)以及价值点(他们点击的原因)。
  3. 草拟 2-3 个标题选项,选出最符合上述规则的一个,然后编写描述、标签、章节。
  4. 自我检查:标题 ≤ 70 字符且关键词靠前;描述钩子的第一句包含关键词;标签 5-15 个且相关;章节从 00:00 开始,按升序排列,至少 3 个,描述性强;全文无长破折号。

参考

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

AlemTuzlak/skills

Use when the user wants to write a blog post about a feature, product change, PR, git diff, or any technical topic - accepts marketing briefs, PRs, git refs, codebase paths, or freeform descriptions as input

AlemTuzlak/skills

Use when the user wants to generate a changelog, release notes, or document what changed between versions, tags, or PRs

AlemTuzlak/skills

Use when writing, editing, or organizing documentation, when planning what docs a feature needs, and whenever planning or implementing a new feature or change in a repo (docs ship with the code). Also use when tempted to write docs without showing the discovered readers to the user, without asking for tone, or without loading simple-english and i-have-adhd. Triggers on "write docs for X", "document this feature", "add a guide", "update the docs", "reorganize the docs", "plan feature X", "implement X", or /docs.

AlemTuzlak/skills

Use when a bug is in play: a test fails, CI is red, an API returns the wrong result, a stack trace appears, or the user says it is broken or fix this. Don't use for a new feature with no failure, for types-only work, or for docs.

AlemTuzlak/skills

Use when the user invokes /i-have-adhd, says they have ADHD, or asks for ADHD-friendly output. Also used as a required writing filter by the docs skill. Don't use for marketing copy or after the user says "stop adhd mode" or "normal mode".

AlemTuzlak/skills

Use when a settled change must be turned into an ordered stack of small blocks before anyone implements. Don't use for unsettled intent, typos, comments, formatting, docs-only work, or writing the implementation itself.

AlemTuzlak/skills

Use when the user wants to write a product update email, feature announcement newsletter, or digest email for users or subscribers

AlemTuzlak/skills

Use when the user wants to turn a raw talking-head / screen-share recording into a finished, edited, annotated video plus a full content package. Removes silences, flags mistakes for the user to cut, transcribes, adds transcript-synced overlays (code, on-screen code highlights, word highlights, lists, comparisons, diagrams, section labels, punch-in zooms), renders with original audio, then generates blog/socials/YouTube content. Triggers on "produce a video", "edit my video", "annotate my recording", "/produce-video".

AlemTuzlak/skills

Use when the user runs /prove-it or says prove it, prove the changes, show me in the browser, or asks to prove a UI or API change. Don't use only because the agent is about to say done, for types-only work, or for docs with no behavior to prove.

AlemTuzlak/skills

Use when the user wants to write, draft, or author an RFC (Request for Comments) / technical design doc for a feature, change, or architectural decision. Interactively interviews the user, grounds the proposal in the actual codebase, presents 2-3 concrete API/code-snippet approaches to choose from, then writes a review-ready RFC. Triggers on "write an RFC", "draft an RFC", "RFC for X", "design doc for X", or /rfc.

AlemTuzlak/skills

Use when the user wants to deeply learn a new topic from scratch. Runs a pre-interview (current knowledge, end-goal proficiency, depth, practice load, background, scope), researches online (articles, niche-influencer blogs, canonical docs, subtopic landscape), then produces a structured markdown course with mandatory visual diagrams, evidence-based learning-science features (retrieval practice, spaced callbacks, worked-example fading, concept ledger, jargon gate, analogy hygiene), and a self-contained interactive HTML mini-course. Triggers on /teach-me, "teach me about X", "I want to learn X", "deep dive on X", "create a course on X", "study X with me".

AlemTuzlak/skills

Use when the change intent is already settled and the agent must map what a behavior change touches before an implementation plan or any code. Use for new features, bug fixes, and refactors that move a boundary. Don't use for typos, comments, formatting, lockfile-only diffs, docs with no code, or while the user is still deciding what they want.

AlemTuzlak/skills

Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker service bundled in this skill and returns transcript.txt, transcript.srt, and word-level transcript.words.json. Also used as a building block by /produce-video. Triggers on "transcribe this video", "get a transcript", "transcribe-video".

AlemTuzlak/skills

Use when the user wants to write a video script for a product demo, feature walkthrough, launch video, or social media video about a feature or product change

相关技能