podcast-summarizer

podcast-summarizer is a skill for Claude Code, Codex from dAAAb/agent-skills. It costs 28 tokens per session (663 once invoked), scanned A, original, MIT.

A tool for turning podcast episodes into transcripts and summaries from Spotify, Apple Podcasts, RSS feeds, or direct MP3 links. RSS is a subscription feed that lists published episodes.

In plain words
What is it for?
Use it to summarize a podcast episode, transcribe its audio, or save the result to a file. It uses Whisper for speech-to-text and an AI service for summarization.
Why use it?
It saves you from listening through an entire episode or manually transcribing it before finding the important points. You can also request only the transcript or choose a summary length and language.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to summarize a podcast episode, transcribe its audio, or save the result to a file. It uses Whisper for speech-to-text and an AI service for summarization.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/daaab/agent-skills/podcast-summarizer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add dAAAb/agent-skills --skill podcast-summarizer
Clone the repo
git clone --depth 1 https://github.com/dAAAb/agent-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for podcast-summarizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/daaab/agent-skills/podcast-summarizer/github.svg)](https://agentmods.dev/skills/daaab/agent-skills/podcast-summarizer)
Your own site
<a href="https://agentmods.dev/skills/daaab/agent-skills/podcast-summarizer"><img src="https://agentmods.dev/badge/skills/daaab/agent-skills/podcast-summarizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for podcast-summarizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/daaab/agent-skills/podcast-summarizer"><img src="https://agentmods.dev/badge/skills/daaab/agent-skills/podcast-summarizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.00663
Opus 5 $0.00014 $0.00331
Sonnet 5 $0.00006 $0.00133
Haiku 4.5 $0.00003 $0.00066

Measured 9d ago against content hash d4dadb35146f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

podcast-summarizer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/summarize_podcast.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -o episode.mp3 "https://rss.soundon.fm/rssf/5c1bdcf0-8ef0-4342-a82e-8803ff85f10c/feedurl/{episode-id}/rssFileVip.mp3"
skills/podcast-summarizer/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Podcast Summarizer 🎙️

Summarize podcast episodes from various platforms.

Supported Platforms

  • Spotify (via page scraping + RSS lookup)
  • Apple Podcasts
  • Direct RSS/MP3 URLs

Usage

# Summarize a Spotify episode
python3 {baseDir}/scripts/summarize_podcast.py "https://open.spotify.com/episode/xxx"

# Summarize from RSS feed
python3 {baseDir}/scripts/summarize_podcast.py "https://example.com/feed.xml" --episode 1

# Summarize from direct MP3
python3 {baseDir}/scripts/summarize_podcast.py "https://example.com/episode.mp3"

Options

  • --language zh - Specify language for transcription (default: auto)
  • --length short|medium|long - Summary length
  • --transcript-only - Output transcript without summary
  • --output FILE - Save to file

Requirements

  • whisper CLI for transcription
  • OPENAI_API_KEY or GEMINI_API_KEY for summarization

How it works

  1. Spotify/Apple: Scrapes episode info, finds RSS feed, downloads audio
  2. RSS: Parses feed, downloads episode audio
  3. MP3: Downloads directly
  4. Transcribe: Uses Whisper for speech-to-text
  5. Summarize: Uses LLM to generate structured summary

Notes

  • Spotify doesn't provide direct audio access; we try to find the original RSS feed
  • For best results, use the podcast's RSS feed directly
  • SoundOn podcasts can often be accessed via their RSS feeds

SoundOn Podcasts (台灣)

SoundOn 是台灣主要的 Podcast 託管平台。RSS feed 格式:

https://feeds.soundon.fm/podcasts/{podcast-id}/soundon.xml

找到 RSS feed 的方法:

  1. 去 player.soundon.fm 搜尋節目
  2. URL 中的 feed_url 參數是 base64 編碼的 RSS URL
  3. 解碼後可取得完整的 RSS feed

音檔 URL 格式:

https://rss.soundon.fm/rssf/{podcast-id}/feedurl/{episode-id}/rssFileVip.mp3

Example: 藝視 Art.Market

# RSS Feed
https://feeds.soundon.fm/podcasts/5c1bdcf0-8ef0-4342-a82e-8803ff85f10c/soundon.xml

# 下載並轉錄最新一集
curl -o episode.mp3 "https://rss.soundon.fm/rssf/5c1bdcf0-8ef0-4342-a82e-8803ff85f10c/feedurl/{episode-id}/rssFileVip.mp3"
whisper episode.mp3 --language zh --model small

Read the full file on GitHub · 77 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 77 lines · 28 tokens per session scan A d4dadb35146f

Subscribe to this mod's changes

podcast-summarizer is a skill published in the GitHub repository dAAAb/agent-skills (2 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 663 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens