Xiaoyuzhou Podcast Notes

把小宇宙（Xiaoyuzhou FM）单集播客转成结构化的 Markdown 笔记。工作流为：解析小宇宙单集链接 → 拿到音频直链、shownotes、章节（有官方转录则直接用）→ 转录音频 → 判断内容类型（财经/科技商业/人物访谈/知识科普/通用）→ 套用对应的笔记模板 → 输出 .md 笔记文件。只要用户给出小宇宙链接（xiaoyuzhoufm.com/episode/...）、或提到"把这期播客整理成笔记""转录小宇宙""生成播客笔记""播客总结/逐字稿/shownotes 整理"，就使用本技能；即便用户没说"skill"二字也应触发。也支持用户已自备音频文件或转录文本，只需生成笔记的场景。

57 stars 4 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add weisi-gu/xiaoyuzhou-podcast-notes --skill xiaoyuzhou-podcast-notes

Manual install

git clone --depth 1 https://github.com/weisi-gu/xiaoyuzhou-podcast-notes.git /tmp/xiaoyuzhou-podcast-notes
mkdir -p ~/.claude/skills
cp -r /tmp/xiaoyuzhou-podcast-notes/. ~/.claude/skills/xiaoyuzhou-podcast-notes

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 小宇宙播客笔记生成器

把一条小宇宙单集链接，变成一份类型匹配、可直接归档的 Markdown 笔记。

## 何时用本技能

- 用户给出小宇宙单集链接（`https://www.xiaoyuzhoufm.com/episode/<id>`），想要笔记/总结/逐字稿；
- 用户已有音频文件或转录文本，想按类型整理成结构化笔记；
- 用户想批量整理某档播客的多期内容。

## 总体流程（五步）

1. **取数据** —— 用 `scripts/fetch_episode.py` 解析链接，拿到标题、播客名、发布日期、时长、音频直链、shownotes（含图文与图表）、章节；若页面自带官方转录，一并取出。
2. **得转录** —— 若第 1 步已有官方转录，直接用；否则下载音频并用 `scripts/transcribe.py` 转录。
3. **判类型** —— 根据播客名 + shownotes + 转录开头，判断内容类型，选定模板（见下）。类型不明确时问用户一次。
4. **写笔记** —— 读取对应模板文件，用转录 + shownotes 逐块填充。**不要**照抄模板里的说明文字，要输出填好的真实内容。
5. **存文件** —— 保存两个成品：`<播客名>-<集标题>-笔记.md` 和 `<播客名>-<集标题>-逐字稿.txt`（逐字稿一并留档），用 `present_files`（若可用）交给用户。

---

## 第 1 步：取数据

```bash
python scripts/fetch_episode.py "<小宇宙链接或episode_id>" --out ./_work
```

脚本会在 `./_work/` 下生成：
- `meta.json` —— 结构化元数据（`title` / `podcast_title` / `pub_date` / `duration_sec` / `audio_url` / `eid` / `has_official_transcript`）
- `shownotes.md` —— shownotes 正文（已转 Markdown，保留图片链接和图表说明）
- `chapters.json` —— 章节时间戳（若有）
- `official_transcript.txt` —— 官方转录（若页面自带）

加 `--download` 会把音频存到 `./_work/audio.m4a`：

```bash
python scripts/fetch_episode.py "<链接>" --out ./_work --download
```

> 说明：本脚本只处理**公开单集**。付费或需登录的内容拿不到直链，此时提示用户改用官方 App 导出音频，再走"已自备音频"路径。

## 第 2 步：得转录（分层兜底，务必拿到真逐字稿）

**核心原则：笔记必须基于真转录稿，不能只靠 shownotes 推断。** 按下面优先级逐级尝试，前一级成功就停：

**① 官方转录**：若 `meta.json` 里 `has_official_transcript` 为真，直接用 `official_transcript.txt`。最准、零成本，跳过 ASR。

**② 云端 Qwen（长音频首选，若配了 `DASHSCOPE_API_KEY`）**：小宇宙音频直链是公网 URL，可不下载、直接转。异步长音频，支持最长 12 小时，一期约 2-5 分钟出稿：

Read the full skill on GitHub

Details

Skill name: xiaoyuzhou-podcast-notes
Repository: weisi-gu/xiaoyuzhou-podcast-notes
License: MIT
Repo updated: 12 July 2026

FAQ

What does the Xiaoyuzhou Podcast Notes skill do?

How do I install the Xiaoyuzhou Podcast Notes skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add weisi-gu/xiaoyuzhou-podcast-notes --skill xiaoyuzhou-podcast-notes. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Xiaoyuzhou Podcast Notes popular?

It lives in weisi-gu/xiaoyuzhou-podcast-notes, which has 57 GitHub stars and 4 forks.

Related skills

Audio Tldr

AugustusW/audio-tldr-skill

Summarize videos, audio files, and podcasts into key takeaways. Give it a YouTube/podcast URL or a local audio/video file — it transcribes locally (cached; repeat requests reuse the transcript) and distills the transcript into key points, summaries, or translations. Use when the user asks to summarize, get key points from, translate, or TL;DR any audio or video content.

Images, Video & AudioIn 1 list

Moyuxl Ecom Image Prompt

AlephAITech/moyuxl-ecom-image-prompt

拆解参考图并把视觉手法迁移到用户产品；或从产品图/基础资料出发，检索可核验信息，策划详情页并输出逐屏生产级豆包生图执行稿。详情页只有产品图/零散身份规格且无完整合格卖点集时，先交付调研卖点大纲并经用户确认。适用于参考反推、主图套系、整套详情页和稀疏资料补全。不用于纯文案、普通修图或翻译。

Images, Video & Audio10

Creator Vibe

bish-x/creator-vibe

Use first for creative work—technical or everyday—when a brief is incomplete or intent is implicit and success depends on taste, voice, feeling, or human experience. Also trigger when literal compliance may lose the point. Do not wait for explicit creative wording. Skip factual lookup, mechanical or exact tasks, and fully specified work.

Images, Video & Audio

Cesium Skills

OpenCesium/Cesium-Skills

Writes native CesiumJS demos for the latest stable Cesium API (async terrain, 3D Tiles, imagery, WebGL2 shaders/effects). Use when creating or migrating Cesium Viewer, layers, terrain, Cesium3DTileset, models, CustomShader, PostProcessStage, materials, particles, or when old Cesium 1.x / WebGL1 demos break. Do not use for non-Cesium GIS or mars3d/SuperMap wrappers.

Images, Video & Audio

Drawing Analyzer

hamzaabduljabbar/construction-drawing-analyzer

Pre-process construction drawing PDF sets into structured text indexes so Claude can answer questions faster, cheaper, and more accurately. Use this skill whenever a user mentions construction drawings, PDF drawings, takeoffs, drawing sets, plans, or wants to extract information from construction documents. Trigger on phrases like "analyze my drawings", "run drawing analyzer", "process these drawings", "how many footings", "what is the slab area", or any question about quantities, elements, or scope from a set of construction drawings. This skill runs once on a drawing set and creates lightwei

Images, Video & Audio

Openai Compatible Imagegen

Syh1906/openai-compatible-imagegen

Generate, edit, and batch-process images through the bundled script and configured API Key provider (OpenAI-compatible, Atlas, xAI, or Gemini). Use for photos, illustrations, product visuals, posters, covers, diagrams, UI references, game art, transparent subjects, reference-image edits, inpainting, multi-reference compositions, and image batches when this local OpenAI-compatible workflow is the requested backend. Do not force this workflow when the user explicitly selects another image tool or backend.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.