Podcast Bridge

Community

Hatari130

podcast-bridge

一个让 AI Agent 订阅、转录、检索并理解全球播客的 Skill。支持添加和同步 RSS 订阅、获取播客单集、免费转录音频、生成章节与摘要、跨单集全文搜索，并将全文稿保存为本地 Markdown 或 Obsidian 知识库。适用于用户提供小宇宙单集链接、RSS 源、播客名称或单集编号，以及要求转录播客、总结单集、提取要点、检索话题、推荐播客、导入订阅、同步订阅或维护 RSS 源等场景。

Overview

Publisher	Hatari130
Repository	`podcast-bridge`
Skill name	`podcast-bridge`
Stars	91
Forks	7
Bundled files	19
License	MIT
Links	Skill source Repository

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.
19 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Hatari130 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Hatari130/podcast-bridge/tree/main
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.

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/Hatari130/podcast-bridge.git \
  .claude/skills/podcast-bridge

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Podcast Bridge 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 Bridge 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 Bridge 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.

podcast-bridge

podcast-bridge 用于管理播客订阅、同步 RSS 单集元数据、转录播客、生成章节、搜索本地播客知识库，并基于全文稿生成摘要或笔记。

核心原则

根据用户请求选择最窄、最直接的工作流：

用户请求	执行动作
提供单集链接并要求全文稿	运行 `python transcribe.py "<url>" --chapters`，返回全文稿路径和基础统计；4h+ 超长节目默认输出上集/下集两份 Markdown。
提供单集链接并要求总结、要点或笔记	先转录，读取生成的全文稿；若输出上/下集，必须读取两份稿件后再总结。
提供 RSS URL 或播客名称并要求添加	添加、同步或列出元数据；默认不要批量转录。
询问某个节目是否聊过某个话题	同步或查询本地库，并区分“全文命中”和“仅标题/简介命中”。
要求推荐播客	读取 `podcast-bridge-feeds/feeds/*.json`，按主题推荐；只有用户明确要求时才导入订阅。
RSS 源损坏或订阅维护	使用 `podcast-bridge-feeds/resolve_feeds.py` 和 `podcast-bridge-feeds/import_feeds.py`。

重要边界：

transcribe.py 是确定性的执行入口，负责转录、章节生成、RSS 入库和搜索。
超过 long_audio_threshold_minutes 的节目默认先拆成 long_audio_parts=2 个大段，再输出 _上集.md 和 _下集.md 两份稿件；最终回复应同时报告两份路径。
摘要需要在读取全文稿之后由 Agent 自己生成；--summary 只是兼容旧参数和表达期望风格，不会稳定地产生摘要文件。
默认 ASR provider 使用 bcut，不需要 API Key。
查询当前状态时，应读取实时文件或 SQLite 数据库，不要依赖文档里的固定订阅数量。
如果用户要求摘要，最终回复必须包含摘要正文，不能只回复“转录完成”。

参考文件路由

只读取当前任务需要的参考文件：

references/transcription.md：单集转录、启动前检查、ASR provider 选项、输出路径。
references/summarization.md：brief、deep、product、investment、Obsidian 等摘要格式。
references/rss-workflows.md：订阅管理、订阅库导入、RSS 同步/列表/搜索/转录。
references/troubleshooting.md：常见失败、编码问题、API/provider 错误、状态查询。
references/project-layout.md：仓库结构、数据文件、路径假设。

常用命令

在 podcast-bridge 项目根目录运行以下命令。config.json 中的 library_dir 会决定使用哪个本地播客库。

bash
python transcribe.py --preflight-only "<episode-url>"
python transcribe.py "<episode-url>" --chapters
python transcribe.py "<episode-url>" --chapters --long-audio-parts 2
python transcribe.py rss subs
python transcribe.py rss sync "<podcast-name>" --limit 50
python transcribe.py rss list "<podcast-name>" --limit 50
python transcribe.py rss search "<podcast-name>" "<topic>" --days 90
python transcribe.py rss transcribe "<podcast-name>" <episode-id> --chapters
python transcribe.py rss transcribe "<podcast-name>" <episode-id> --chapters --long-audio-parts 2

如果当前工作目录不在项目根目录，应使用 transcribe.py 的绝对路径。

维护内置订阅库：

bash
cd podcast-bridge-feeds
python resolve_feeds.py bootstrap
python resolve_feeds.py add "Latent Space" --category ai --country us
python resolve_feeds.py validate feeds/
python import_feeds.py --all

交付要求

转录完成后，尽量报告生成的全文稿路径和基础统计信息，包括时长、分段数量、字数或字符数。超长节目可能生成上集/下集两份 Markdown，必须同时报告两份路径。

回答搜索类问题时，必须说明覆盖范围：有多少单集具备可搜索全文，有多少单集只有标题/简介元数据可搜索。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Podcast Bridge AI skill do?

Why use Podcast Bridge on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hatari130/podcast-bridge/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Podcast Bridge?

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 Bridge?

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

Is the Podcast Bridge AI skill free?

Yes. It is published on GitHub by Hatari130 under the MIT license. 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

Video Editing

affaan-m

CommunityPopular

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

Ai Presenter Video

Make a verified AI presenter video from script + image.

Audiocraft Audio Generation

NousResearch

OrganizationPopular

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

Brag Slim

Launch video from a project or URL, upstream-maintained.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

podcast-bridge

核心原则

参考文件路由

常用命令

交付要求

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now