● Community
jordanrendric
⚡ Instant
Claude Video Vision
by jordanrendric · jordanrendric/claude-video-vision
Make Claude actually understand a video — frames + transcript + scene segmentation, fed in a token-efficient layout.
The skill takes a video file or URL, extracts keyframes (scene-aware), aligns transcript segments, and presents the bundle to Claude for QA, summary, or content extraction. Smart-sampling avoids blowing the context window.
Why use it
Key features
- Scene-aware keyframe extraction
- Whisper-quality transcript alignment
- Per-scene token budget
- Works with local files or YouTube URLs
- Output: structured JSON for downstream skills
Live Demo
What it looks like in practice
ready
Use Cases
Real-world ways to use Claude Video Vision
When to use: Conference talk just dropped; you want notes without watching it.
Flow
-
Ingest
Point skill at the URL.✓ Copied
→ Frames + transcript ready
-
Ask
Ask focused questions; skill scopes to relevant scenes.✓ Copied
→ Precise answers with timestamps
Outcome: Targeted understanding without re-watching.
Combinations
Pair with other MCPs for X10 leverage
Save the structured note output for later reference
Combine claude-video-vision with filesystem: Save the structured note output for later reference✓ Copied
Cost & Limits
What this costs to run
- API quota
- Bound by transcription cost
- Tokens per call
- Mid (sampled, not full video)
- Monetary
- Free skill; transcription/model costs
- Tip
- Use shorter scenes when QA is targeted; use long-window mode for summary
Security
Permissions, secrets, blast radius
Minimum scopes: fs-read fs-write
Credential storage: API keys for transcription provider in env
Data egress: Transcription provider
Never grant: process private video without consent
Troubleshooting
Common errors and fixes
Transcript misaligned
Lower scene-segmentation threshold; transcript may be off due to music
Alternatives
Claude Video Vision vs others
| Alternative | When to use it instead | Tradeoff |
|---|
| Manual notes | Talk is short | Doesn't scale to many videos |