agentsclimarketplace

Case 03823

Skill knownasnaffy/prompthound/dataset/case_03823

A fast, offline static risk analysis CLI for AI agent skill files. Detects malicious instructions, steganographic payloads, and dangerous capability chains.

Install
npx -y skills add knownasnaffy/prompthound --skill case_03823

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Summarize podcast episodes into concise, actionable insights. Use when users want to get the key points from a podcast episode without listening to the entire audio. Supports audio files, URLs, RSS feeds, and podcast platform links.

SKILL.md

2.4 KB, 569 tokens by cl100k_base, as published. Nobody here has run it

Cleanup Review

python scripts/_cleanup.py is an optional cleanup helper for the Podcast Summarize skill. It may recursively remove ~/.cache/skill_tmp, ~/.skill_state. Show the exact paths first, explain whether they are skill-private temporary paths or user state, and run the cleanup only after the user confirms.

Podcast Summarize

Transform podcast episodes into structured, actionable summaries.

When to Use

  • User wants podcast episode key points
  • User needs to quickly review podcast content
  • User prefers reading over listening
  • User wants to extract actionable insights from podcasts
  • User shares podcast and wants a summary accompany

Supported Inputs

  1. Audio file path - Local MP3, M4A, WAV files
  2. Audio URL - Direct link to audio file
  3. YouTube video - Podcast on YouTube
  4. RSS feed URL - Podcast RSS feed
  5. Podcast episode URL - Link to episode on podcast platforms

Summary Format

Provide summaries in this structure:

## 🎙️ 播客摘要

### 基本信息
- **标题**: [Episode Title]
- **时长**: [Duration]
- **日期**: [Publish Date]
- **播客**: [Podcast Name]

### 💡 核心要点 (3-5条)
1. [Key point 1]
2. [Key point 2]
3. ...

### 📝 详细摘要
[2-3 paragraph summary]

### 🎯 行动项 (如有)
- [Actionable insight 1]
- [Actionable insight 2]

### 🔗 相关链接
- [Mentioned resources]

Process

  1. Audio Extraction

    • For YouTube: Use yt-dlp to extract audio
    • For local files: Verify format and duration
    • For URLs: Download if needed

  2. Transcription

    • Use Whisper (local or API) for transcription
    • Support multiple languages
    • Handle long audio (chunk if needed)

  3. Summarization

    • Extract key themes
    • Identify actionable insights
    • Note timestamps for important sections
    • Highlight guest/host insights

Tips

  • Ask user preference: Brief (3 bullets) vs Detailed (full summary)
  • Offer to extract specific segments if user has timestamps
  • Provide follow-up questions based on content
  • Suggest related podcasts if available

Example Triggers

  • "summarize this podcast"
  • "这个播客讲的什么"
  • "podcast summary"
  • "播客摘要"

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.