YouTube Watcher

v1.0.0

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

0· 1.2k·1 current·1 all-time
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
high confidence
!
Purpose & Capability
The declared purpose (fetch and read YouTube transcripts) legitimately requires a downloader like yt-dlp, which is requested. However, the SKILL.md expects a local script (python3 {baseDir}/scripts/get_transcript.py) to exist and be executed; no such script or other code files are present in the package manifest. That makes the skill unable to perform its task as provided and suggests missing or out-of-band components.
!
Instruction Scope
Runtime instructions explicitly tell the agent to execute a local Python script and then read its output. Because the script is not present, the instructions are incomplete. The instructions do not attempt to access unrelated system files or credentials, but they do assume ability to run local code (which could be arbitrary) and to access the network to fetch YouTube content.
Install Mechanism
Registry install spec lists a Homebrew formula to install yt-dlp (reasonable for the declared purpose). The SKILL.md metadata also lists a pip install option for yt-dlp, but the registry metadata provided to you included only the brew install — a minor inconsistency. The install source (brew yt-dlp) is a standard release channel and not high-risk.
Credentials
No environment variables, credentials, or config paths are requested, which is proportional for a transcript-fetching tool. The only requirement is the yt-dlp binary, which fits the stated function.
Persistence & Privilege
The skill does not request always: true or other elevated persistence. It is user-invocable and allows autonomous invocation (platform default), which is expected for skills. No system-wide modifications are described.
What to consider before installing
Do not install or enable this skill until the missing code is provided and reviewed. The SKILL.md tells the agent to run a local script (scripts/get_transcript.py) but the package contains no code files — this could be an accidental omission or indicate the skill expects out-of-band files. Before proceeding, ask the publisher for the script source or full repository, and review the script contents to ensure it only calls yt-dlp and processes transcripts (no secrets exfiltration or arbitrary shell exec). Confirm how yt-dlp will be installed (brew vs pip) and be aware the skill will need network access to contact YouTube; if you proceed, restrict the environment and inspect the script for any unexpected network endpoints or file accesses.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

📺 Clawdis
Binsyt-dlp

Install

Install yt-dlp (brew)
Bins: yt-dlp
brew install yt-dlp
latestvk972p3j48d208ja4fbk8hv48hh80vgmm
1.2kdownloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

YouTube Watcher

Usage

Get Transcript

Retrieve the text transcript of a video.

python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"

Examples

Summarize a video:

  1. Get the transcript:
    python3 {baseDir}/scripts/get_transcript.py "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
    
  2. Read the output and summarize it for the user.

Find specific information:

  1. Get the transcript.
  2. Search the text for keywords or answer the user's question based on the content.

Notes

  • Requires yt-dlp to be installed and available in the PATH.
  • Works with videos that have closed captions (CC) or auto-generated subtitles.
  • If a video has no subtitles, the script will fail with an error message.

Comments

Loading comments...