← Back to Skills Marketplace
Gemini Yt Video Transcript
by
Oliver Drobnik
· GitHub ↗
· v1.0.4
3407
Downloads
3
Stars
13
Active Installs
5
Versions
Install in OpenClaw
/install gemini-yt-video-transcript
Description
Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (no timestamps).
README (SKILL.md)
Gemini YouTube Video Transcript
Create a verbatim transcript for a YouTube URL using Google Gemini.
Output format
- First line: YouTube video title
- Then transcript lines only in the form:
Speaker: text
Requirements
- No time codes
- No extra headings / lists / commentary
Usage
python3 {baseDir}/scripts/youtube_transcript.py "https://www.youtube.com/watch?v=..."
Options:
--out \x3Cpath>Write transcript to a specific file (default: auto-named in the workspaceout/folder).
Delivery
When chatting: send the resulting transcript as a document/attachment.
Usage Guidance
This skill appears coherent for its stated purpose, but consider privacy and key-handling before installing: the script sends the video URL (and relies on Gemini fetching the video content) to Google’s generative-language API using your GEMINI_API_KEY, so private or DRM-protected videos may be exposed to Google and may fail to be ingested. Only provide a GEMINI_API_KEY you trust this use for; run the script in a controlled workspace; examine the code (it’s small and uses only standard Python libs); and if the key is later compromised, revoke/rotate it. If you need transcripts without sending media to Google, this skill is not suitable.
Capability Analysis
Type: OpenClaw Skill
Name: gemini-yt-video-transcript
Version: 1.0.4
The skill is designed to transcribe YouTube videos using Google Gemini. The `SKILL.md` provides clear, benign instructions without any prompt injection attempts against the OpenClaw agent. The `scripts/youtube_transcript.py` script securely handles the `GEMINI_API_KEY` from environment variables, makes network calls exclusively to legitimate Google Gemini and YouTube oEmbed endpoints, and includes a robust `_safe_output_path` function to restrict file output to the skill's workspace or temporary directories, preventing arbitrary file writes. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation.
Capability Assessment
Purpose & Capability
Name/description match the actual behavior: the script calls Google Gemini to generate a transcript from a YouTube URL. Declared requirements (python3, GEMINI_API_KEY) are appropriate for that functionality.
Instruction Scope
SKILL.md instructs running the included Python script which: fetches the YouTube title via oEmbed, sends a prompt and the video URL to the Gemini API (using a 'file_data' file_uri so Gemini can ingest the video), and writes a transcript file under the workspace or /tmp. The actions are within scope for transcription, but the script explicitly sends the video URL (and relies on Gemini fetching the video content) to Google — a privacy/third-party data-sharing consideration rather than an incoherence.
Install Mechanism
No install spec; instruction-only with a small Python script that uses only the standard library (urllib, json, pathlib). No external downloads or archives, so installation risk is low.
Credentials
Only GEMINI_API_KEY is required. The script optionally reads OPENCLAW_WORKSPACE or TMPDIR for safe output path resolution; no unrelated secrets or excessive env variables are requested.
Persistence & Privilege
The skill is not always-enabled, does not modify other skills or global agent settings, and only writes transcript files into controlled workspace or /tmp locations. No elevated persistence is requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install gemini-yt-video-transcript - After installation, invoke the skill by name or use
/gemini-yt-video-transcript - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.4
Fix metadata: moltbot→openclaw so registry picks up GEMINI_API_KEY and python3 requirements
v1.0.3
Sandbox --out to workspace/tmp, default output to workspace/gemini-yt-video-transcript/out/
v1.0.2
Remove --debug; default output to workspace out/; README explains file_url ingestion
v1.0.1
Add GitHub/ClawdHub cross-links in README
v1.0.0
Initial release (renamed from video-transcript; best-practice structure)
Metadata
Frequently Asked Questions
What is Gemini Yt Video Transcript?
Create a verbatim transcript for a YouTube URL using Google Gemini (speaker labels, paragraph breaks; no time codes). Use when the user asks to transcribe a YouTube video or wants a clean transcript (no timestamps). It is an AI Agent Skill for Claude Code / OpenClaw, with 3407 downloads so far.
How do I install Gemini Yt Video Transcript?
Run "/install gemini-yt-video-transcript" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Gemini Yt Video Transcript free?
Yes, Gemini Yt Video Transcript is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Gemini Yt Video Transcript support?
Gemini Yt Video Transcript is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Gemini Yt Video Transcript?
It is built and maintained by Oliver Drobnik (@odrobnik); the current version is v1.0.4.
More Skills