Podcast To Article logo

Podcast To Article

Community
bozhouDev
podcast-to-article

将播客、YouTube 视频或音视频内容转化为高质量文章。通过 NotebookLM 进行多轮深度对话提炼内容,提供写作方向选择,自动去 AI 味,生成吸引人的标题。当用户提到「把这个视频/播客写成文章」「帮我把这个内容转成文字」「根据这个视频写一篇文章」「播客转文章」「视频转文章」或者给了一个 YouTube/播客链接并要求写作时,使用此 Skill。

Overview

PublisherbozhouDev
Repositorybozhou-skills
Skill namepodcast-to-article
Stars
78
Forks
7
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bozhouDev on GitHub. Read the source before you install it.

Installation

Install the Podcast To Article AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bozhouDev/bozhou-skills/tree/main/podcast-to-article
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bozhouDev/bozhou-skills.git /tmp/bozhou-skills
mkdir -p .claude/skills
cp -r /tmp/bozhou-skills/podcast-to-article .claude/skills/podcast-to-article
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Podcast To Article in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Podcast To Article on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Podcast To Article is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

播客/视频转文章 Skill

将播客、视频、音频内容通过 NotebookLM 深度研究后,转化为一篇有血有肉的文章。

依赖

  • notebooklm CLI(已安装且已登录)
  • humanizer-zh skill(去 AI 味)
  • dbs-content skill(内容创作诊断)
  • 用户的写作风格 skill(可选,如 bozhou-writing-style)

工作流程总览

添加源 → 概览调研 → 提出4个方向 → 用户选择 → 深度调研(存档) → 写作 → 去AI味 → 生成标题  → 生成配图

Phase 1: 准备源材料

用户会给你一个 URL(YouTube、播客链接)或告诉你 NotebookLM 里已经有了。

如果需要添加源:

bash
# 创建笔记本(或用户指定已有的)
notebooklm create "主题名" --json

# 设置上下文
notebooklm use <notebook_id>

# 添加源
notebooklm source add "https://youtube.com/..." --json

# 等源处理完毕
notebooklm source list --json  # 确认 status 为 ready

如果源还在 processing,等它变成 ready 再进入下一步。可以用 notebooklm source wait <source_id> 等待。


Phase 2: 概览调研(1 轮)

向 NotebookLM 提一个全面的概览问题,快速摸清内容全貌。

bash
notebooklm ask "Please give me a comprehensive overview: 1) Who are the key people and their backgrounds? 2) What is the main topic/theme? 3) What are the top 3-5 key takeaways? 4) What is the structure/flow of the conversation?" --json

从返回的 JSON 中提取 conversation_id,后续所有提问都用 -c <conversation_id> 保持对话连贯。

解析回答,提取核心信息:人物、主题、关键论点、对话结构。


Phase 3: 提出 4 个写作方向

根据概览内容,提出 4 个不同的写作角度。每个方向要包含:

  • 方向名称(一句话概括切入点)
  • 聚焦内容(这个方向重点写什么)
  • 目标读者(什么人看了会觉得有用)

用 AskUserQuestion 让用户选择 1-2 个方向。

提方向的原则:

  • 不要做"全面总结"型方向——那是读书笔记,不是文章
  • 每个方向要有明确的切入点和情绪基调
  • 可以从这些维度找角度:方法论、人物故事、反常识观点、踩坑经验、行业趋势
  • 方向之间要有差异,不要只是换个说法

Phase 4: 深度调研(6 轮以上)

根据用户选择的方向,设计 6 轮以上有针对性的提问。确保了解清楚。

每轮提问都用 --json -c <conversation_id> 保持上下文:

bash
notebooklm ask "具体问题..." --json -c <conversation_id>

关键:把每轮 Q&A 写入临时文档。 在用户项目目录下创建一个调研笔记:

文件路径:当前工作目录/podcast-research-<日期>.md

文档格式:

markdown
# 调研笔记:[内容标题]
日期:YYYY-MM-DD
来源:[URL]
选定方向:[用户选的方向]

## Round 1: [子主题]
**问题:** ...
**回答:** ...
**关键提取:** (3-5 个要点)

## Round 2: [子主题]
...

每轮调研完成后立即写入文档,不要攒到最后。


Phase 5: 写作

5.1 设计开头钩子

遵循 CLAUDE.md 中「钩子写作指南」的三要素框架和自检标准。

在写全文之前,先单独构思 2-3 个不同风格的开头钩子。针对播客/视频转文章,额外注意:

  • 场景型特别适合有故事性的访谈(例:他坐在 Joshua Tree 的石头上,三个小时没动)
  • 金句型可以直接用嘉宾说过的最有力的一句话开场
  • 每个钩子都要带上具体的例子说明承诺和可信度如何体现

用 AskUserQuestion 让用户选一个开头方向,或者告诉你他想要哪种感觉。

5.2 撰写全文

基于调研笔记和选定的开头,撰写完整文章。

写作要求:

  • 字数 5000-8000 字(根据内容丰富程度调整)
  • 不是视频笔记或内容摘要——是用视频素材为原料的独立文章
  • 要有主线(贯穿全文的核心论点或叙事弧线)
  • 细节要具体:名字、数字、时间线、具体故事
  • 引用嘉宾原话时用 加粗 标注
  • 外文引用必须中文化: 目标读者是中文用户,不要在正文中放大段英文原话。所有英文引用直接翻译成中文并加粗,不保留英文原文。专有名词(品牌名、人名、产品名如 SpaceX、Tesla)可保留英文,但描述性句子、金句、观点必须用中文呈现。极短且读者普遍认识的词(如 maybe、yes)可酌情保留

如果用户有写作风格 skill(如 bozhou-writing-style): 加载该 skill 并严格遵循其风格要求。写之前先读一遍 skill 的核心规则和禁用清单。

如果没有特定风格 skill: 用清晰、自然、口语化的中文写作。避免商业黑话和套话。

5.3 确认文章保存位置

用 AskUserQuestion 问用户文章保存到哪里,或者根据上下文推断(比如用户之前的文章都放在某个目录)。

文件命名规则: 文件名直接使用文章标题(如 OpenAI 的 PM 说:PM 不是领导岗,20 人以下的团队不需要 PM.md),不要用 slug 或英文缩写。标题确定后立即重命名文件。


Phase 6: 去 AI 味

文章写完后,调用 humanizer-zh skill 进行去 AI 味处理:

/humanizer-zh 对文件 [文章路径] 进行去AI味优化

如果用户有写作风格 skill,在调用 humanizer-zh 时一并提及,让它结合风格要求优化。

去 AI 味重点关注:

  • 对称排比(三段式、四段式并列结构)
  • "不是...而是..."过度使用
  • 工整的金句/slogan(听起来像能印在 T 恤上的话)
  • AI 高频词(恰恰、近乎、至关重要、值得注意的是)
  • 段尾的总结升华(每段最后一句话都在"扣题")
  • 过度使用破折号做并列

Phase 7: 生成标题

最后一步:为文章生成 3-5 个标题选项。

好标题的特征:

  • 有信息量——看完标题就知道文章大概讲什么
  • 有钩子——让人想点进去看
  • 不是标题党——承诺和内容匹配
  • 长度 15-30 字

标题公式参考:

  • [人名]:[具体事件/数字],[一个启发]
  • [反常识结论]:[一个人怎么做到的]
  • [具体数字/事实] + [背后的故事/方法]

用 AskUserQuestion 给出 3-5 个标题让用户选择,或者用户可以自己改。选定后更新文章标题。


Phase 8: 生成文章配图

文章标题确定后,调用 article-illustrator skill 为文章生成配图。

/article-illustrator [文章路径]

article-illustrator 会自动完成以下工作:

  • 分析文章结构,判断配图位置和类型
  • 根据文章内容自主选择视觉风格
  • 生成图片并插入文章

如需指定配图密度或类型,可传参数:

/article-illustrator [文章路径] --density rich
/article-illustrator [文章路径] --type infographic

配图完成后确认用户是否满意。

最后将链接youtube链接放到文章尾部


检查清单

文章完成后自查:

  • 开头钩子是否满足三要素(粉丝画像明确、有承诺、有可信度)
  • 是否有贯穿全文的主线(不是罗列要点)
  • 细节是否具体(有名字、数字、场景)
  • 嘉宾原话是否用加粗标注
  • 是否已去 AI 味
  • 标题是否吸引人且诚实
  • 字数是否在 2000-5000 之间
  • 调研笔记是否已保存
  • 配图是否已通过 article-illustrator 生成并插入文章

Frequently asked questions

What does the Podcast To Article AI skill do?

将播客、YouTube 视频或音视频内容转化为高质量文章。通过 NotebookLM 进行多轮深度对话提炼内容,提供写作方向选择,自动去 AI 味,生成吸引人的标题。当用户提到「把这个视频/播客写成文章」「帮我把这个内容转成文字」「根据这个视频写一篇文章」「播客转文章」「视频转文章」或者给了一个 YouTube/播客链接并要求写作时,使用此 Skill。

Why use Podcast To Article on TypingMind?

Because you install it once and use it with any model. Podcast To Article is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Podcast To Article in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bozhouDev/bozhou-skills/tree/main/podcast-to-article. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Podcast To Article?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Podcast To Article?

As many as you like. As long as a model supports skills, you can use Podcast To Article with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Podcast To Article AI skill free?

It is published on GitHub by bozhouDev. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇