Ingest, analyze, search, edit, and monitor video and audio streams.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "videodb" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/videodb/SKILL.md 2. Save it as ~/.claude/skills/videodb/SKILL.md 3. Reload skills and tell me it's ready
Please ingest this product launch video URL, build visual and temporal indexes, and find all moments mentioning pricing and release date. Return timestamps and playable clip links.
A list of relevant moments with match descriptions, timestamps, and auto-generated playable clip links.
Transcode this batch of course videos to 1080p, 30fps, H.264, then automatically add Chinese subtitles, a branded intro overlay, and background music. Export publish-ready versions.
Publish-ready videos with standardized format, subtitles, and branding elements applied.
Connect to the store surveillance RTSP live stream, detect when the queue exceeds 10 people or the checkout area is unattended for more than 3 minutes, and send real-time alerts.
Continuous live-stream analysis with event descriptions, timestamps, and real-time alerts when conditions are met.
Perception + memory + actions for video, live streams, and desktop sessions.
Before running any VideoDB code, change to the project directory and load environment variables:
from dotenv import load_dotenv
load_dotenv(".env")
import videodb
conn = videodb.connect()
This reads VIDEO_DB_API_KEY from:
.env file in current directoryIf the key is missing, videodb.connect() raises AuthenticationError automatically.
Do NOT write a script file when a short inline command works.
When writing inline Python (python -c "..."), always use properly formatted code — use semicolons to separate statements and keep it readable. For anything longer than ~3 statements, use a heredoc instead:
python << 'EOF'
from dotenv import load_dotenv
load_dotenv(".env")
import videodb
conn = videodb.connect()
coll = conn.get_collection()
print(f"Videos: {len(coll.get_videos())}")
EOF
When the user asks to "setup videodb" or similar:
pip install "videodb[capture]" python-dotenv
If videodb[capture] fails on Linux, install without the capture extra:
pip install videodb python-dotenv
The user must set VIDEO_DB_API_KEY using either method:
export VIDEO_DB_API_KEY=your-key.env file: Save VIDEO_DB_API_KEY=your-key in the project's .env fileGet a free API key at console.videodb.io (50 free uploads, no credit card).
Do NOT read, write, or handle the API key yourself. Always let the user set it.
# URL
video = coll.upload(url="https://example.com/video.mp4")
# YouTube
video = coll.upload(url="https://www.youtube.com/watch?v=VIDEO_ID")
# Local file
video = coll.upload(file_path="/path/to/video.mp4")
# force=True skips the error if the video is already indexed
video.index_spoken_words(force=True)
text = video.get_transcript_text()
stream_url = video.add_subtitle()
…
Record polished web app UI demo videos for walkthroughs, tutorials, and showcases.
Refine retrieved context iteratively to improve subagent understanding and output quality.
Unify multi-channel notifications for routing, deduplication, escalation, and inbox consolidation.
Audit, plan, and implement SEO improvements for better search visibility.
Create iOS liquid glass interfaces with dynamic visuals and interactive morphing.
Fetches up-to-date framework docs for setup, APIs, and code examples.
Enable Claude to analyze video frames and audio for richer understanding.
Turn videos into numbered frame grids and transcripts for AI analysis.
Analyze videos with transcripts, summaries, scene breakdowns, clips, and Q&A.
Search videos, ask questions, and extract insights with natural language.
Edit footage, structure videos, add AI enhancements, and polish final cuts.
Turn videos into searchable, citable scene graphs for AI analysis.