← Back to Skills Marketplace
video-transcriber
by
jpengcheng523-netizen
· GitHub ↗
· v1.0.0
· MIT-0
110
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install jpeng-video-transcriber
Description
Transcribe speech from videos
README (SKILL.md)
Video Transcriber
Transcribe speech from videos
When to Use
- User needs ai related functionality
- Automating transcription tasks
- Video operations
Usage
python3 scripts/video_transcriber.py --input \x3Cinput> --output \x3Coutput>
Configuration
Set required environment variables:
export TRANSCRIPTION_API_KEY="your-api-key"
Output
Returns JSON with results:
{
"success": true,
"data": {}
}
Usage Guidance
This skill's README tells you to run a local Python script and to set TRANSCRIPTION_API_KEY, but the package you were given contains no script and the metadata doesn't declare that env var. That could be sloppy packaging or an attempt to make the agent fetch/run external code. Before installing or providing any API key: (1) ask the publisher for the missing script or a full source listing, (2) verify which transcription service the API key is for and only provide a scoped/test key, (3) prefer running in a sandbox, and (4) avoid giving high-privilege credentials. If the author can't explain the mismatches, treat the skill as unsafe.
Capability Analysis
Type: OpenClaw Skill
Name: jpeng-video-transcriber
Version: 1.0.0
The skill bundle contains metadata and documentation for a video transcription tool. The instructions in SKILL.md are consistent with the stated purpose and do not contain any indicators of prompt injection, malicious commands, or data exfiltration. While the execution script (scripts/video_transcriber.py) is referenced, it was not provided for analysis; however, the documentation itself is benign.
Capability Assessment
Purpose & Capability
The name/description (video transcription) matches the requested TRANSCRIPTION_API_KEY in SKILL.md, which is appropriate for a transcription service. However, the registry metadata declares no required env vars or credentials while the instructions explicitly require TRANSCRIPTION_API_KEY — an inconsistency that should be explained by the author.
Instruction Scope
SKILL.md tells the agent to run `python3 scripts/video_transcriber.py`, but the skill bundle contains no scripts or code. That means the instructions either assume code exists elsewhere (not provided) or will cause the agent to fetch or generate code at runtime — a behavior that broadens scope and risk. The instructions also ask for an API key but give no guidance about the vendor/service or where the key will be sent.
Install Mechanism
There is no install spec and no code files — lowest install risk. However, the missing script increases runtime ambiguity (agent may try to obtain or run external code).
Credentials
SKILL.md requires a TRANSCRIPTION_API_KEY (reasonable for a transcription integration) but the skill metadata lists no required env vars or primary credential. The discrepancy between declared requirements and runtime instructions is a red flag.
Persistence & Privilege
Skill is not always-enabled and uses default autonomous invocation behavior. It does not request persistent system-wide configuration or declare elevated privileges in the manifest.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install jpeng-video-transcriber - After installation, invoke the skill by name or use
/jpeng-video-transcriber - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of jpeng-video-transcriber:
- Transcribes speech from video files using AI.
- Provides a command-line script for easy usage and automation.
- Outputs transcription results in JSON format.
- Requires API key configuration via environment variable.
- Suitable for automating video transcription tasks.
Metadata
Frequently Asked Questions
What is video-transcriber?
Transcribe speech from videos. It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.
How do I install video-transcriber?
Run "/install jpeng-video-transcriber" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is video-transcriber free?
Yes, video-transcriber is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does video-transcriber support?
video-transcriber is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created video-transcriber?
It is built and maintained by jpengcheng523-netizen (@jpengcheng523-netizen); the current version is v1.0.0.
More Skills