Videodb skills
Shared library of AI agent skills — works across Claude Code, Cursor, Codex, Windsurf, OpenCode, and Google Antigravity via a single universal installer.
npx -y skills add newmindsgroup/ai-agent-skills-library --skill videodb-skillsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Upload, stream, search, edit, transcribe, and generate AI video and audio using the VideoDB SDK.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.7 KB, 747 tokens by cl100k_base, as published. Nobody here has run it
VideoDB Skills
Purpose
The only video skill your agent needs. Upload any video, connect real-time streams, search inside by what was said or shown, build complex editing workflows with overlays, generate AI media, add subtitles, and get instant streaming links — all via the VideoDB Python SDK.
When to Use This Skill
- User wants to upload and process videos from YouTube, URLs, or local files
- User needs to search for moments by speech or visual scenes
- User asks for transcription, subtitles, or subtitle styling
- User wants to edit clips — trim, combine, add text/image/audio overlays
- User needs AI-generated media (images, video, music, sound effects, voiceovers)
- User wants to transcode, change resolution, or reframe for social platforms
- User needs real-time screen or audio capture with AI transcription
- User asks for playable streaming links for any video output
Setup
Step 1: Install the skill
npx skills add video-db/skills
Step 2: Run setup
/videodb setup
The agent guides API key setup ($20 free credits, no credit card), installs the SDK, and verifies the connection.
Alternatively, set the API key manually:
export VIDEO_DB_API_KEY=sk-xxx
Step 3: Install the SDK
pip install "videodb[capture]" python-dotenv
Capabilities
| Capability | Description |
|---|---|
| Upload | Ingest videos from YouTube, URLs, or local files |
| Search | Find moments by speech (semantic/keyword) or visual scenes |
| Transcripts | Generate timestamped transcripts from any video |
| Edit | Combine clips, trim, add text/image/audio overlays |
| Subtitles | Auto-generate and style subtitles |
| AI Generate | Create images, video, music, sound effects, and voiceovers from text |
| Capture | Real-time screen and audio capture with AI transcription |
| Transcode | Change resolution, quality, aspect ratio, or reframe for social platforms |
| Stream | Get playable HLS links for anything you build |
Examples
Upload and transcribe:
"Upload https://www.youtube.com/watch?v=FgrO9ADPZSA and give me a transcript"
Search across videos:
"Search for 'product demo' in my latest video"
Add subtitles:
"Add subtitles with white text on black background"
Multi-clip editing:
"Take clips from 10s-30s and 45s-60s, add a title card, and combine them"
AI media generation:
"Generate background music and overlay it on my video"
Real-time capture:
"Capture my screen and transcribe it in real-time"
Reframe for social:
"Convert this to vertical for Instagram Reels"
Repository
https://github.com/video-db/skills
Version: 1.1.0 Maintained By: VideoDB
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.