Video Intelligence

Download videos and get transcripts, summaries, or metadata from YouTube, TikTok, Instagram, and X (Twitter). Use when the user shares a video URL and wants...

Security Scan

The skill mostly does what it claims (download videos, read captions, and fall back to OpenAI audio transcription) but the package metadata omits required binaries and the optional OpenAI API key the scripts actually use — and the fallback behavior uploads audio off your machine to OpenAI, so you should understand that before installing.

Purpose & Capability

The skill's name and description match the code: yt-dlp is used to fetch captions/downloads, a Python script parses captions, and curl is used to call OpenAI for audio transcription. However, the registry metadata lists no required binaries or env vars while SKILL.md and the scripts require yt-dlp, python3, curl (and optionally ffmpeg) and optionally OPENAI_API_KEY. That metadata omission is an incoherence and should be corrected by the publisher.

Instruction Scope

SKILL.md and scripts stay within the stated purpose: fetching captions, downloading audio/video, parsing captions, and calling OpenAI's transcription endpoint as a documented fallback. The README explicitly warns about audio uploads and gives guidance. The scripts write cached output to /tmp/video-intel and use $HOME for a local yt-dlp fallback; they do not read other system config or unrelated secrets.

Install Mechanism

There is no formal install spec in the registry (instruction-only skill). SKILL.md includes a curl command to download yt-dlp from GitHub releases and suggests apt install for ffmpeg. Downloading a binary with curl is common but higher-risk than using a distribution package manager; the instructions will write to ~/bin which is benign but should be performed consciously by the user.

Credentials

The registry metadata claims no required env vars, but the script will require OPENAI_API_KEY when captions are unavailable and it falls back to the OpenAI transcription API. That credential request is proportionate to the fallback behavior, but the omission from the declared requirements is an inconsistency. Users must be aware that providing OPENAI_API_KEY causes audio files to be uploaded to api.openai.com.

Persistence & Privilege

No special persistence or privileged flags are requested (always:false). The skill caches files under /tmp/video-intel and does not modify other skills or system-wide agent settings. It does not try to auto-enable itself or gain elevated privileges.

What to consider before installing

Before installing or running this skill: (1) Understand privacy: when captions are not available the script downloads audio and uploads it to OpenAI's transcription API (api.openai.com) using OPENAI_API_KEY — do not provide that key if you don't want audio leaving your machine. (2) The registry metadata does not list required binaries or the optional OPENAI_API_KEY even though the SKILL.md and scripts require yt-dlp, python3, curl (and ffmpeg for some sites) — confirm you have/are willing to install those. (3) Prefer installing yt-dlp and ffmpeg via your OS/package manager rather than blindly running the provided curl | chmod command. (4) Inspect the script locally before running, and consider running it in a confined environment (container/VM) if you have sensitive data. (5) Ask the publisher to update the skill metadata to declare the required binaries and the OPENAI_API_KEY dependency so the registry accurately reflects what will be needed.

video-intel

Downloads videos and extracts transcripts using yt-dlp (captions) with OpenAI Whisper fallback.

Required Dependencies

Dependency	Purpose	Required?
yt-dlp	Fetch captions and download audio/video	✅ Always
python3	Parse VTT/SRT caption files	✅ Always
curl	Call OpenAI Whisper API	✅ For Whisper fallback
ffmpeg	Extract audio from TikTok/Instagram/X	⚠️ Non-YouTube only
OPENAI_API_KEY	Authenticate with OpenAI Whisper API	⚠️ Only if captions unavailable

Install binaries:

# yt-dlp
curl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o ~/bin/yt-dlp && chmod +x ~/bin/yt-dlp

# ffmpeg (Debian/Ubuntu)
sudo apt install ffmpeg

⚠️ Privacy Notice — OpenAI Audio Upload

When captions are unavailable (common for TikTok, Instagram, X), the script downloads the audio and uploads it to OpenAI's transcription API (https://api.openai.com/v1/audio/transcriptions). This means:

• Audio content leaves your machine and is sent to OpenAI
• Requires OPENAI_API_KEY to be set
• If you don't want external transmission: don't set OPENAI_API_KEY, or use a local transcription model

YouTube videos almost always have captions and will not trigger an upload.

Script

~/.openclaw/skills/video-intel/scripts/video-intel.sh

Workflows

Get transcript

~/.openclaw/skills/video-intel/scripts/video-intel.sh transcript <url>

• YouTube: uses built-in captions/auto-subs (fast, no audio download or external upload)
• TikTok/Instagram/X: downloads audio → uploads to OpenAI Whisper for transcription
• Preferred language: --lang pt for Portuguese

Get video info

~/.openclaw/skills/video-intel/scripts/video-intel.sh info <url>

List available caption tracks

~/.openclaw/skills/video-intel/scripts/video-intel.sh captions <url>

Download video

~/.openclaw/skills/video-intel/scripts/video-intel.sh download <url> [--format audio|720p|best]

After getting transcript

• Summary: Summarize in 3-5 bullet points
• Key quotes: Extract most notable quotes
• Full summary: Write a paragraph summary with context
• Translation: Translate to the user's language if different

Notes

• YouTube auto-captions are usually available even without ffmpeg
• TikTok/Instagram/X require ffmpeg for audio extraction
• Large videos (>25MB audio) may hit OpenAI's file size limit — use --format audio to get a smaller mp3
• Output cached in /tmp/video-intel/ by default