An advanced AI tool that converts podcast audio and transcripts into structured knowledge assets, interactive visual reports, and cross-episode matrices.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install podcast-digest
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install podcast-digest using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Podcast Digest?
The Podcast Digest skill is a sophisticated analysis framework designed to turn audio content into high-value knowledge assets. As a featured part of the Openclaw Skills ecosystem, it moves beyond simple summaries by dissecting podcasts into layered insights, including core arguments, supporting evidence, and hidden tensions between speakers. Whether you are analyzing a single episode or performing longitudinal research across multiple shows, this skill provides the structure needed for deep cognitive processing.
By leveraging this skill, developers and researchers can automate the extraction of gold-standard quotes and actionable insights. It integrates seamlessly with visualization tools to generate Mermaid diagrams, interactive HTML reports, and presentation-ready slides, making it an essential component for anyone looking to maximize their learning efficiency from audio media.
Podcast Digest Use Cases
- Creating deep-dive study notes from technical or philosophical podcast episodes.
- Performing cross-episode research to track how a specific concept evolves over time across different guests.
- Generating professional web-based reports or PPTs to share industry insights with a team.
- Automating the population of personal knowledge bases like Obsidian or Notion with structured, bi-directionally linked data.
How Podcast Digest Works
- Input Detection: The skill identifies the source material, which can be a raw audio file, a text transcript, or even a podcast title and platform for web-based retrieval.
- Layered Extraction: Content is analyzed through five distinct levels (L1-L5), ranging from basic claims to implicit assumptions and future research directions.
- Semantic Tagging: The system automatically assigns metadata tags for domains, characters, concepts, and controversial points to ensure easy searchability.
- Visualization & Reporting: Based on user preference, the skill generates Mermaid relationship graphs, interactive HTML reports, or Markdown files with YAML frontmatter.
Podcast Digest Setup
To get started with this skill within the Openclaw Skills framework, follow these steps:
# Navigate to your agent's skills directory
cd skills/
# Clone the podcast-digest repository
git clone https://github.com/open-claw/podcast-digest.git
# Ensure dependencies for audio processing or web search are active
npm install
Ensure that the references/ directory contains the necessary templates for Mermaid and HTML report generation.
Podcast Digest Data Schema & Taxonomy
The skill organizes extracted information into a rigid taxonomy to facilitate easy integration with other Openclaw Skills.
| Data Layer | Fields | Description |
|---|---|---|
| Basic Info | Name, Date, Guests | Core identity of the podcast episode. |
| Content L1-L5 | Claims, Evidence, Tensions | Multi-tier logical breakdown of the discourse. |
| Insight Cards | Golden Quotes, Scenarios | High-impact statements with deep-dive application contexts. |
| Graph Schema | Nodes, Edges, Frequency | Data structures for Mermaid and D3.js knowledge graphs. |
| Export Specs | HTML, MD, PPT | Templates for various output formats. |
Podcast Digest Advanced Features
- Multi-episode research mode that builds a comparative matrix between different episodes and hosts.
- Interactive Q&A card generation that creates flashcards based on specific timestamps and concepts.
- Automated knowledge graph construction showing the evolution of ideas across a series.
- Full support for bi-directional linking (
[[concept]]) and YAML metadata for seamless PKM integration.
SKILL.md
Loading
Related Openclaw Skills
Spawner
The Spawner skill enables the delegation of complex, long-running tasks to independent sub-agents using efficient model routing.
Active Self-Improvement
An autonomous self-optimization loop that enables AI agents to learn from past errors and successes to update their own internal protocols.
Task Extractor
A robust workflow skill designed to parse complex user messages into discrete, trackable, and verifiable action items.
UniProfit Mail Assistant
A specialized AI agent skill for sending verified emails through the UniProfit API using Openclaw Skills.
Rate Limit Guard
A protective layer for AI agents that prevents 429 rate limit loops and optimizes token usage during API failures.
Frustration Translator
A sophisticated tool designed to detect emotional charge in user prompts and translate them into clear, actionable technical instructions for AI agents.
Featured*
