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

No licenceAuto-check: notesMedia & Creative

Install Podcast

skills CLI
$ npx skills add zarazhangrui/personalized-podcast --skill podcast -a claude-code

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

GitHub CLI
$ gh skill install zarazhangrui/personalized-podcast podcast --agent claude-code

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

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

Facts

Skill name
podcast
GitHub stars
438
Token cost
~2.3k tokens
SKILL.md length
1,175 words
Files
12 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

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

  • Works in 12 steps: Install dependencies → Create config with default voices → Get Fish Audio API key → …
  • Tasks that involve Podcasting
  • SKILL.md covers Path convention, First-time setup, Generating an episode and RSS feed setup (only when user…, plus 1 more section
  • Runs Python scripts from its folder; calls gh, python and brew; reaches username.github.io; needs FISH_API_KEY

What it does

Podcast is an agent skill from zarazhangrui/personalized-podcast. Generate a podcast episode from content you provide. Paste text, point to local files, or describe a topic. Two AI hosts discuss it in a natural conversation. Listen locally or in your favorite podcast app via RSS.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including scripts (for example `PROMPT.md`, `README.md` and `config/config.example.yaml`).

It sits in Media & Creative, covering Podcasting and Text to speech and voice. It works with FFmpeg. The repository describes itself as: Turn any content into a personalized AI podcast. NotebookLM-style, except you control the script, voices, and hosts. Listen in Apple Podcasts, Spotify, or any podcast app.

When your agent uses it

  • Tasks that involve Podcasting
  • Tasks that involve Text to speech and voice

Example prompts

  • “/podcast”

Requirements

  • Python 3
  • A credential in FISH_API_KEY

Workflow steps

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

  1. Install dependencies
  2. Create config with default voices
  3. Get Fish Audio API key
  4. Done
  5. Read the content
  6. Write the podcast script
  7. Generate audio
  8. Play the audio
  9. Post-generation tips
  10. Create a public GitHub repo
  11. Enable GitHub Pages
  12. Update config

What it can do on your machine

Read from SKILL.md and the folder at commit 5c6449a. 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

    Ships 5 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • python
    • brew
    • apt
    • python3
    • pip
    • ffmpeg
    • git

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • username.github.io

    Also links to:

    • fish.audio
    • podcasters.spotify.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • FISH_API_KEY

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

Context cost

Podcast loads about 2.3k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 1,175 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~56
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:50
    ll it: `brew install ffmpeg` (macOS) or `sudo apt install ffmpeg` (Linux).
  • NoteMentions a .env fileSKILL.md:69
    Then create the .env file and open it:
  • NoteMentions a .env fileSKILL.md:72
    "FISH_API_KEY=your_key_here" > DATA_DIR/.env
  • NoteMentions a .env fileSKILL.md:73
    open DATA_DIR/.env
  • NoteMentions a .env fileSKILL.md:78
    ste API keys in the chat. Always use the .env file.
  • NoteMentions a .env fileSKILL.md:232
    **"API key not found"** - Check DATA_DIR/.env has a valid FISH_API_KEY
  • NoteRuns commands with sudoSKILL.md:233
    - Run: `brew install ffmpeg` (macOS) or `sudo apt install ffmpeg` (Linux)

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,175 words (~2,304 tokens).

name
podcast

Read the full SKILL.md on GitHub

Files

SKILL.md and 11 other files (scripts) in the repository root of zarazhangrui/personalized-podcast.

  • SKILL.md
  • .gitignore
  • PROMPT.md
  • README.md
  • config/config.example.yaml
  • examples/sample_config.yaml
  • scripts/bootstrap.py
  • scripts/publish.py
  • scripts/requirements.txt
  • scripts/speak.py
  • scripts/utils.py
  • templates/feed_template.xml

Open the folder on GitHubat commit 5c6449a

Compare with similar skills

Podcast 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Podcast this skillzarazhangrui/personalized-podcast438—~2.3kAutomated safety check: NotesNone
Video Podcast Makerdtsola/xiaoyaosearch1k—~3.4kAutomated safety check: PassMIT
Book Sales VideoKianzzz/book-sales-video218—~3.2kAutomated safety check: PassMIT
Video Assemblezenstory-ai/video-recap-skills561—~1.7kAutomated safety check: PassMIT
Video Cutzenstory-ai/video-recap-skills561—~1.6kAutomated safety check: PassMIT
Z Qwen Audio Studiotjxj/z-skills548—~716Automated safety check: PassNone

Similar skills

  • Video Podcast Maker

    dtsola/xiaoyaosearch

    Turns a topic into a 4K horizontal video podcast through research, scripting, text-to-speech, Remotion rendering and background music, and can learn styles from references.

    1k GitHub stars~3.4k tokensUpdated 9 days ago
    Media & CreativeAuto-check passed
  • Book Sales Video

    Kianzzz/book-sales-video

    从书名或飞书多维表格中的成稿文案出发,结合微信读书资料与公开点评创作图书带货/书评短视频,并用豆包 TTS、Pexels、Codex 生图和本机 OpenChatCut 完成配音、配图、双语字幕、音效、动效、BGM、可编辑初稿与按需导出。用户提出“根据一本书做带货视频”“读取飞书文案制作图书视频”“写书评口播并自动剪成抖音视频”“仿参考样式做图书推荐短视频”时使用;仅查书、仅写普通书评或无关剪辑…

    218 GitHub stars~3.2k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Video Assemble

    zenstory-ai/video-recap-skills

    合成视频解说最终成片:把旁白音频铺到源视频上,按旁白窗口压低原声,生成 SRT / ASS 字幕并可烧录, 最后做响度标准化。作为最终合成阶段使用。输入源视频、ttsmeta.json 与旁白位置; 输出 recap 成片和字幕。触发词:视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。

    561 GitHub stars~1.7k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • Video Cut

    zenstory-ai/video-recap-skills

    把长视频按 Agent 选择的原片区间剪成短片。作为两阶段创作流程中的剪辑环节,读取 clipplan.json 与源视频, 输出 editedsource.mp4;随后 Agent 按输出时间线写 narration.json。支持单视频与多视频(sources manifest)拼剪, 本工具不读取、不映射旁白。

    561 GitHub stars~1.6k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • Z Qwen Audio Studio

    tjxj/z-skills

    A skill your agent uses when creating complete generated audio with qwen-audio-3.1-tts-next, including podcasts, radio drama, advertisements, multiple speakers, reference voices, ambience, sound…

    548 GitHub stars~716 tokensUpdated 19 days ago
    Media & CreativeAuto-check passed
  • Podcast

    team-attention/plugins-for-claude-natives

    Generate Korean podcast episodes from any source (URLs, tweets, articles, PDFs) — analyzes content, writes a script, generates audio via OpenAI TTS, converts to MP4, and auto-uploads to YouTube.

    827 GitHub stars~1.5k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed

Works with

Questions about Podcast

What does Podcast do?

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

When should I use Podcast?

Podcast fits situations like: tasks that involve Podcasting; tasks that involve Text to speech and voice.

How do I install Podcast in Claude Code?

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

How do I install Podcast in Codex?

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

Can I use Podcast 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 zarazhangrui/personalized-podcast --skill podcast -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, .gemini/skills/podcast, .github/skills/podcast and .opencode/skills/podcast in your project.

What does Podcast need to run?

Going by SKILL.md and its folder, Podcast needs Python for the scripts in its folder, the command-line tools its instructions call (gh, python, brew, apt, python3 and pip) and credentials named FISH_API_KEY. Our summary lists: Python 3; A credential in FISH_API_KEY.

Does Podcast access the network?

SKILL.md names 3 domains. In commands or code: username.github.io; the agent is likely to contact it when it follows the instructions. As links in the text: fish.audio and podcasters.spotify.com. This is read from the text; nothing was executed.

Is Podcast safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo; mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Podcast use?

No licence was found for Podcast or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Podcast use?

About 2.3k tokens (SKILL.md is roughly 9.2k 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?

Skills that share tags, products or a category with Podcast: Video Podcast Maker (dtsola/xiaoyaosearch, 1k stars), Book Sales Video (Kianzzz/book-sales-video, 218 stars), Video Assemble (zenstory-ai/video-recap-skills, 561 stars) and Video Cut (zenstory-ai/video-recap-skills, 561 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Podcast?

zarazhangrui (a GitHub user) maintains it in zarazhangrui/personalized-podcast, which has 438 GitHub stars. The repository was last updated on April 8, 2026.

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