Read Podcast Workflow logo

Read Podcast Workflow

Community
SpaceZephyr
read-podcast-workflow

播客处理一站式工作流。支持两种入口: (1) 直接处理:提供 YouTube 链接,直接进入处理流程 (2) 更新检查:获取关注博主的最新更新,用户挑选后处理 功能:字幕提取 → read-content-digest 处理 → 自动保存飞书知识库。 触发词:"获取播客更新"、"处理这个播客"、"播客工作流"、"有什么新播客"。

Overview

PublisherSpaceZephyr
Repositoryread-buddy
Skill nameread-podcast-workflow
Stars
85
Forks
25
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 SpaceZephyr on GitHub. Read the source before you install it.

Installation

Install the Read Podcast Workflow 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/SpaceZephyr/read-buddy/tree/main/read-podcast-workflow
  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/SpaceZephyr/read-buddy.git /tmp/read-buddy
mkdir -p .claude/skills
cp -r /tmp/read-buddy/read-podcast-workflow .claude/skills/read-podcast-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Read Podcast Workflow 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 Read Podcast Workflow 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 Read Podcast Workflow 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.

播客处理工作流

从 YouTube 到飞书发布的一站式播客处理流程。

两种入口

入口 A:获取播客更新(推荐)

用户说"获取播客更新"或"有什么新播客"时:

获取更新 → 展示列表 → 用户选择 → 字幕提取 → [询问] → Content-Digest → 飞书

入口 B:直接处理链接

用户提供 YouTube 链接时:

YouTube 链接 → 字幕提取 → [询问] → Content-Digest → 飞书

入口 A:获取播客更新流程

Step A1: 获取更新列表

运行命令:

bash
python3 /Users/ugreen/.claude/skills/read-youtube-feed/scripts/get_updates.py --days 2

输出格式:

📺 最近 2 天共有 N 个新播客更新:

1. 【Lenny's Podcast】
   📌 视频标题
   🕐 2026-01-30 15:00
   🔗 https://www.youtube.com/watch?v=xxx
   📝 简要描述...

2. 【No Priors】
   ...

Step A2: 用户选择

展示列表后询问:

请选择要处理的播客(输入序号,如 1 或 1,3),或输入 "跳过":

等待用户选择后,进入 Step 1。


入口 B:直接处理流程

Step 1: 提取 YouTube 字幕

运行命令:

bash
python3 /Users/ugreen/.claude/skills/read-youtube-transcript/scripts/get_transcript.py "YOUTUBE_URL"

输出:Markdown 格式的字幕文本

Step 2: 询问是否处理

字幕提取成功后,必须询问用户:

字幕提取成功!是否使用 read-content-digest 处理成精华内容?
- 处理后会生成:标题 + 核心观点列表 + 精华片段
- 处理完成后自动保存到飞书「每日播客推荐」

等待用户确认后再继续。

Step 3: Content-Digest 处理

参考 /Users/ugreen/.claude/skills/read-content-digest/SKILL.md 的完整流程。

关键格式要求(v2 — 2026-05-12 更新):

每篇播客摘要使用如下统一格式,所有字段都必须填写:

markdown
文章标题:MMDD-文章中文一句话主题(如 0512-如何搭建个人 AI OS)
嘉宾:[嘉宾名](Twitter @handle)
频道:[频道名]
日期:YYYY-MM-DD
主题:[一句话主题描述,30 字内]
播客地址:[YouTube 完整 URL]

# 核心观点

1、[观点]。[完整的逻辑阐述,包含推理过程,2-4 句话]

2、[观点]。[完整的逻辑阐述,包含推理过程,2-4 句话]

...(10-15 条)

# 精彩片段

[使用 Style B 对话式访谈格式,挑选 3-5 个最精彩的片段,保留嘉宾原话翻译]

字段说明:

  • 文章标题:用作飞书文档的标题和本地文件名前缀,格式 MMDD-中文一句话主题
  • 嘉宾:如果能查到 Twitter 账号附上,查不到就只写名字
  • 日期:视频在 YouTube 的发布日期,不是处理日期
  • 主题:一句话能让人决定要不要看的描述

Step 4: 保存到本地

保存位置: /Users/ugreen/Documents/obsidian/每日播客/

文件命名: MMDD-嘉宾名-主题关键词.md

示例:0130-Peter-Steinberger-AI编程革命.md

Step 5: 自动保存到飞书

运行命令:

bash
python3 /Users/ugreen/.claude/skills/feishu-wiki/scripts/save_to_wiki.py \
  --file "/Users/ugreen/Documents/obsidian/每日播客/MMDD-xxx.md" \
  --title "MMDD:嘉宾名 X 栏目名:一句话观点" \
  --parent "TOSJwKzxTiFdiRk0aducHNBFntg"

父节点 Token: TOSJwKzxTiFdiRk0aducHNBFntg(每日播客推荐)

Step 6: 返回结果并询问图片

处理完成后,向用户展示:

✅ 播客处理完成!

📝 本地文件:/Users/ugreen/Documents/obsidian/每日播客/MMDD-xxx.md
📤 飞书文档:https://my.feishu.cn/wiki/xxx

核心观点数:N 条
精华片段数:N 个

---

是否要将核心观点转为图片海报?(适合小红书/朋友圈分享)

Step 7: 转换为图片(可选)

如果用户确认要转为图片,调用 markdown-to-image Skill:

  1. 提取短文版本:只保留标题 + 核心观点列表(不含精华片段)
  2. 优化格式:
    • 添加 emoji 序号(1️⃣ 2️⃣ 3️⃣)
    • 精简每条观点到 1-2 句话
    • 控制总字数在 500 字以内
  3. 使用浏览器 MCP 操作 Madopic:
  4. 告知用户图片已下载到下载目录

快速使用示例

用户说:

处理这个播客 https://www.youtube.com/watch?v=xxxxx

Agent 执行:

  1. 提取字幕 ✓
  2. 询问用户 → 用户确认
  3. Content-Digest 处理 ✓
  4. 保存本地 ✓
  5. 保存飞书 ✓
  6. 返回结果

错误处理

错误处理方式
字幕提取失败告知用户视频可能没有字幕,询问是否手动提供文本
飞书写入失败检查权限,提示用户添加应用到知识库协作者
网络超时重试一次,仍失败则告知用户

关注的 YouTube 频道

数据来源:Zara's AI Learning Library

分类频道
AI 教育Andrej Karpathy, Anthropic, Lex Fridman
AI 产品Lenny's Podcast, Peter Yang, The MAD Podcast, Every
VC 投资Y Combinator, Latent Space, South Park Commons, No Priors, a16z
大厂研究Google DeepMind, Google for Developers, Stanford GSB
Vibe CodingMckay Wrigley, Tiago Forte, The Pragmatic Engineer
AI 新闻The AI Daily Brief, TBPN, Brett Malinowski

共 21 个频道

添加新频道:编辑 /Users/ugreen/.claude/skills/read-youtube-feed/scripts/get_updates.py

依赖的 Skills

  • read-youtube-feed:获取博主更新
  • read-youtube-transcript:字幕提取
  • read-content-digest:内容处理
  • feishu-wiki:飞书写入
  • markdown-to-image:转换为图片海报(可选)

配置

配置项值
本地保存路径/Users/ugreen/Documents/obsidian/每日播客/
飞书父节点TOSJwKzxTiFdiRk0aducHNBFntg(每日播客推荐)
观点数量10-15 条
更新检查天数2 天

Frequently asked questions

What does the Read Podcast Workflow AI skill do?

播客处理一站式工作流。支持两种入口: (1) 直接处理:提供 YouTube 链接,直接进入处理流程 (2) 更新检查:获取关注博主的最新更新,用户挑选后处理 功能:字幕提取 → read-content-digest 处理 → 自动保存飞书知识库。 触发词:"获取播客更新"、"处理这个播客"、"播客工作流"、"有什么新播客"。

Why use Read Podcast Workflow on TypingMind?

Because you install it once and use it with any model. Read Podcast Workflow 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 Read Podcast Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpaceZephyr/read-buddy/tree/main/read-podcast-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Read Podcast Workflow?

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 Read Podcast Workflow?

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

Is the Read Podcast Workflow AI skill free?

It is published on GitHub by SpaceZephyr. 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 👇