Download a TikTok, Instagram Reel, X video, or short-form video URL locally, extract/transcribe the audio, analyse the teaching or workflow inside it, and tu...
Security Analysis
high confidenceThe skill is coherent and purpose-aligned, but users should know it runs local video tools, may send extracted audio to OpenAI if an API key is present, and creates a persistent generated skill that should be reviewed.
The stated purpose matches the artifacts: download a user-provided short-video URL, extract/transcribe audio, analyze the workflow, and create an OpenClaw skill. The local commands and optional provider transcription are expected for that purpose.
Use is scoped to cases where the user provides a social-video link and wants a skill from it. Because the resulting skill is derived from untrusted video/transcript content, users should review the generated SKILL.md before relying on it.
There is no install spec and metadata declares no required binaries, but the script expects yt-dlp and ffmpeg to already be available. This is a setup/provenance note rather than suspicious behavior.
The script optionally uses OPENAI_API_KEY and uploads the extracted audio to OpenAI for transcription. This is disclosed and proportionate to the transcription feature.
The workflow creates a new skill folder under skills/<skill-name>/, which is expected for a skill-generation tool but creates persistent agent instructions that should be reviewed.
Guidance
Install only if you are comfortable running yt-dlp and ffmpeg on user-selected video URLs. If OPENAI_API_KEY is set, the extracted audio will be sent to OpenAI for transcription; unset the key to avoid that. Always review the generated skill before using it because it is derived from untrusted video content.
Latest Release
v1.0.0
Add social video download, transcription, and skill creation workflow
More by @olliewazza
Published by @olliewazza on ClawHub
