Agent skill

Podcast Script

by digoal in digoal/blog

将 Markdown 文章转换成 N 人播客脚本(1~4人),输出为 .txt 文件保存至当前项目的 markdown/ 目录。触发条件:用户提到"转成播客"、"生成播客脚本"、"把这篇文章做成播客"、"播客对话"、"podcast script"、"N个人的播客",或者上传了一个 markdown 文件并希望以播客形式呈现。即使用户只说"帮我把这篇文章转成播客",也应使用本…

GPL-2.0Auto-check passedMedia & Creative

Install Podcast Script

skills CLI
$ npx skills add digoal/blog --skill podcast-script -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog podcast-script --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/podcast-script .claude/skills/podcast-script && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
podcast-script
GitHub stars
8.6k
Token cost
~747 tokens
SKILL.md length
149 words
Files
1
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

将 Markdown 文章转换成 N 人播客脚本(1~4人),输出为 .txt 文件保存至当前项目的 markdown/ 目录。触发条件:用户提到"转成播客"、"生成播客脚本"、"把这篇文章做成播客"、"播客对话"、"podcast script"、"N个人的播客",或者上传了一个 markdown 文件并希望以播客形式呈现。即使用户只说"帮我把这篇文章转成播客",也应使用本…

  • Works in 5 steps: :读取输入 → :设计主持人角色 → :撰写播客脚本 → …
  • Tasks that involve Podcasting
  • SKILL.md covers 功能定位, 执行流程 and 特殊情况处理
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Podcast Script is an agent skill from digoal/blog. 将 Markdown 文章转换成 N 人播客脚本(1~4人),输出为 .txt 文件保存至当前项目的 markdown/ 目录。触发条件:用户提到"转成播客"、"生成播客脚本"、"把这篇文章做成播客"、"播客对话"、"podcast script"、"N个人的播客",或者上传了一个 markdown 文件并希望以播客形式呈现。即使用户只说"帮我把这篇文章转成播客",也应使用本 skill。默认输出中文脚本,除非用户明确指定其他语言。

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Podcasting and Markdown. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve Podcasting
  • Tasks that involve Markdown

Example prompts

  • “生成播客脚本”
  • “把这篇文章做成播客”
  • “podcast script”
  • “/podcast-script”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. :读取输入
  2. :设计主持人角色
  3. :撰写播客脚本
  4. :质量自检
  5. :保存文件

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Podcast Script loads about 747 tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 149 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~747

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit 69fb793, republished under its GPL-2.0 licence (© digoal). 149 words, ~747 tokens.

Download SKILL.mdSave it as .claude/skills/podcast-script/SKILL.md (or your agent's skills folder).
name
podcast-script
description
将 Markdown 文章转换成 N 人播客脚本(1~4人),输出为 .txt 文件保存至当前项目的 markdown/ 目录。触发条件:用户提到"转成播客"、"生成播客脚本"、"把这篇文章做成播客"、"播客对话"、"podcast script"、"N个人的播客",或者上传了一个 markdown 文件并希望以播客形式呈现。即使用户只说"帮我把这篇文章转成播客",也应使用本 skill。默认输出中文脚本,除非用户明确指定其他语言。

Podcast Script Generator — 播客脚本生成 Skill

功能定位

将任意 Markdown 文章转换为自然、真实、有节奏感的多人播客对话脚本:

  • 支持 1~4 位主持人/嘉宾(默认 1 人)
  • 默认输出中文,用户指定语言时切换
  • 保留英文术语,不强行翻译(如 token、agent、GPT、ROI、API 等)
  • 输出格式:纯文本 .txt,保存到 markdown/ 目录

执行流程

Step 1:读取输入

从用户提供的 Markdown 文件(或消息中的内容)提取:

  1. 文章核心议题:主题是什么?有哪些关键论点?
  2. 重要数据与案例:哪些事实/数字值得在对话中重点提及?
  3. 文章结构段落:有几个自然节点适合转化为对话切换点?
  4. 英文术语清单:列出所有需要保留的英文词汇(不翻译)

用户如果没有指定人数,默认使用 1 人。


Step 2:设计主持人角色

根据人数分配角色,风格要有差异化,形成自然的对话张力:

人数角色分工建议
1 人独白式主持,自问自答,穿插感慨和停顿
2 人一位主持人(引导节奏)+ 一位嘉宾(补充深度/提出疑问)
3 人主持人 + 技术嘉宾(偏专业) + 行业嘉宾(偏实践/投资)
4 人主持人 + 3位嘉宾,每人代表不同视角(乐观/保守/中立/行动派)

为每位 speaker 设定:

  • 姓名(中文名,自然亲切)
  • 一句话身份定位(开场时自报家门)
  • 性格标签:如"喜欢追问细节"、"善于大局观类比"、"偶尔质疑共识"

Step 3:撰写播客脚本
脚本结构
[开场] 主持人热场,介绍今天的话题和嘉宾 —— 约 5~8 轮对话
[正文] 按文章段落展开讨论,每个核心论点对应一轮对话 —— 占脚本 70%
[收尾] 总结观点、展望或留下开放性问题 —— 约 3~5 轮对话
脚本格式

每行固定格式:

Speaker X(姓名): [对话内容]

示例:

Speaker 1(林晓): 大家好,欢迎来到今天的节目。我是主持人林晓,今天我们聊一个最近在科技圈很火的话题——token 到底是什么?为什么有人说它是 AI 时代的新货币?我旁边坐着两位嘉宾,先请两位自我介绍一下。

Speaker 2(陈博): 我是陈博,在一家 AI 创业公司做产品,日常跟 API、token 计费打交道,可以说是每天都在算 token 的成本。

Speaker 3(吴静): 我是吴静,做二级市场投资,最近一直在研究 AI 产业链的投资逻辑,token 出海这个叙事让我很感兴趣。

Speaker 1(林晓): 好,那我们直接切入。陈博,你先给我们普及一下,token 到底是什么?
对话写作原则

自然性:

  • 允许口语化表达:「对对对」「你说的这个…」「等等,我插一句」「这让我想到…」
  • 允许对话打断、接话、情绪性反应(但不夸张)
  • 避免每句话都是完整陈述句,要有问句、感叹、追问

节奏感:

  • 每个 speaker 发言长度控制在 2~6句话,避免一人独白过长
  • 每隔 4~6 轮切换话题时,由主持人做过渡(如"刚才说的是…,我们再聊聊…")
  • 在重要数据或反常结论出现时,嘉宾要有反应(惊讶/质疑/共鸣)

信息密度:

  • 不要把文章所有内容都塞进去,选最有讨论价值的 5~8 个核心点展开
  • 数据要口语化呈现:不说"增长了159%",说"差不多翻了一倍半"或精确说"159%,快翻倍了"
  • 专有名词第一次出现时,嘉宾或主持人要顺带一句简短解释

英文术语保留规则:

  • 不翻译:token、agent、API、prompt、output、input、cache、LLM、ROI、ARR、MoE、benchmark 等
  • 自然融入中文句子中:「跑一个 agent 任务消耗的 token 量…」
  • 首次出现时可加一句口语解释,如「token,就是模型处理文字时的最小计量单位」

Step 4:质量自检

输出前检查:

  • 每位 speaker 的发言风格是否有差异(不能所有人说话一个腔调)?
  • 有没有连续超过 6 句的独白(破坏对话感)?
  • 关键数据是否用口语化方式表达?
  • 英文术语是否保留且未被翻译?
  • 开场是否自然介绍了嘉宾和话题?
  • 结尾是否有收束感(总结、展望或开放问题)?
  • 脚本整体长度是否合理?(2人约 40~60 轮对话;3~4人适当增加)

Step 5:保存文件
输出路径:markdown/podcast-{文章标题关键词}-{人数}speakers.txt

示例:markdown/podcast-token-economics-2speakers.txt

  • 如果 markdown/ 目录不存在,先用 bash_tool 创建:mkdir -p markdown
  • 文件名用小写英文或拼音,空格用短横线替代
  • 用 create_file 工具写入,完成后用 present_files 展示给用户

特殊情况处理

1 人独白播客:

去掉 Speaker 编号差异,改为单人自言自语风格,加入停顿感:

Speaker 1(主持人姓名, 默认姓名: 德哥): 今天想聊一个问题……其实说起来,这件事让我想了很久。[停顿] token,这个词最近出现的频率越来越高……

用户指定其他语言:

将所有中文对话内容替换为目标语言,但 专有名词(包括中文公司名)保持原样,如 DeepSeek、MiniMax、阿里巴巴等。

文章过长(>3000字):

提炼文章中最重要的 5~8 个论点,不必逐段覆盖。优先保留:反常结论、数据亮点、核心争议点。

文章过短(<500字):

补充背景知识和延伸讨论,让对话有足够深度,不要简单复述原文。

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skills_for_claude_web/podcast-script of digoal/blog.

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Podcast Script next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Podcast Script compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Podcast Script this skilldigoal/blog8.6k—~747Automated safety check: PassGPL-2.0
Bilibili Transcribechubbyguan/chubbyskills1.2k1 repos~578Automated safety check: NotesMIT
Douyin Transcribechubbyguan/chubbyskills1.2k1 repos~551Automated safety check: NotesMIT
Podcast Transcript FetcherVarnan-Tech/opendirectory6741 repos~1.9kAutomated safety check: NotesMIT
Podcastzarazhangrui/personalized-podcast437—~2.3kAutomated safety check: NotesNone
Podpullxiaoleiy/podpull146—~962Automated safety check: PassMIT

Similar skills

  • Bilibili Transcribe

    chubbyguan/chubbyskills

    哔哩哔哩视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub starsUsed in 1 repo~578 tokens
    Media & CreativeAuto-check: notes
  • Douyin Transcribe

    chubbyguan/chubbyskills

    抖音视频 → 下载 → 转录 → 存为 Markdown 的完整工作流. An agent skill from chubbyguan/chubbyskills.

    1.2k GitHub starsUsed in 1 repo~551 tokens
    Media & CreativeAuto-check: notes
  • Podcast Transcript Fetcher

    Varnan-Tech/opendirectory

    A skill your agent uses when fetching, searching, or analyzing transcripts from Lenny's Podcast, Dwarkesh Podcast, Cheeky Pint, 20VC, or A16z Podcast.

    674 GitHub starsUsed in 1 repo~1.9k tokens
    Media & CreativeAuto-check: notes
  • Podcast

    zarazhangrui/personalized-podcast

    Generate a podcast episode from content you provide. An agent skill from zarazhangrui/personalized-podcast.

    437 GitHub stars~2.3k tokensUpdated 6 mo ago
    Media & CreativeAuto-check: notes
  • Podpull

    xiaoleiy/podpull

    A skill your agent uses when the user wants to download a podcast episode's audio file (mp3/m4a) to disk — from an Apple Podcasts show or episode link, a raw RSS feed, or a 小宇宙/xiaoyuzhou episode…

    146 GitHub stars~962 tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Xiaoyuzhou Download

    gainubi/wechat-skills

    Download Xiaoyuzhou FM podcast episode audio files from xiaoyuzhoufm.com/episode links.

    170 GitHub stars~551 tokensUpdated 4 mo ago
    Media & CreativeAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 10 days ago
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated 10 days ago
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated 10 days ago
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed

Questions about Podcast Script

What does Podcast Script do?

将 Markdown 文章转换成 N 人播客脚本(1~4人),输出为 .txt 文件保存至当前项目的 markdown/ 目录。触发条件:用户提到"转成播客"、"生成播客脚本"、"把这篇文章做成播客"、"播客对话"、"podcast script"、"N个人的播客",或者上传了一个 markdown 文件并希望以播客形式呈现。即使用户只说"帮我把这篇文章转成播客",也应使用本…. Podcast Script is an agent skill from digoal/blog.

When should I use Podcast Script?

Podcast Script fits situations like: tasks that involve Podcasting; tasks that involve Markdown.

How do I install Podcast Script in Claude Code?

Run `npx skills add digoal/blog --skill podcast-script -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/podcast-script in digoal/blog) into .claude/skills/podcast-script in your project. Claude Code loads it when a task matches its description.

How do I install Podcast Script in Codex?

Run `npx skills add digoal/blog --skill podcast-script -a codex`. Or copy the skill folder (skills/skills_for_claude_web/podcast-script in digoal/blog) into .agents/skills/podcast-script in your project. Codex loads it when a task matches its description.

Can I use Podcast Script in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill podcast-script -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/podcast-script, .gemini/skills/podcast-script, .github/skills/podcast-script and .opencode/skills/podcast-script in your project.

What does Podcast Script need to run?

SKILL.md names no scripts, command-line tools or credentials: Podcast Script is instructions for the agent only.

Does Podcast Script access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Podcast Script safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Podcast Script use?

Podcast Script is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Podcast Script use?

About 747 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Podcast Script?

Skills that share tags, products or a category with Podcast Script: Bilibili Transcribe (chubbyguan/chubbyskills, 1.2k stars), Douyin Transcribe (chubbyguan/chubbyskills, 1.2k stars), Podcast Transcript Fetcher (Varnan-Tech/opendirectory, 674 stars) and Podcast (zarazhangrui/personalized-podcast, 437 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Podcast Script?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.