Find where a video stutters, from repeated frames

Sync and qualityScreen recordingTool missed

0:12owner-made · agentic-video gallery (owner-made)

Proof frames

Click a frame to seek

Tool calls

1 calls · agentic-video 0.3.1

check_frame_cadenceimac · 343 ms

Arguments

{
  "source": "$CLIP"
}

Result

{
  "ok": true,
  "data": {
    "frame_rate": 10,
    "frames": 120,
    "held_frames": 87,
    "ranges": [
      {
        "start_sec": 6.2,
        "end_sec": 7.2,
        "frames": 10,
        "duplicate_frames": 7,
        "effective_fps": 3
      },
      {
        "start_sec": 8.5,
        "end_sec": 9,
        "frames": 5,
        "duplicate_frames": 4,
        "effective_fps": 2
      },
      {
        "start_sec": 9.8,
        "end_sec": 10.8,
        "frames": 10,
        "duplicate_frames": 7,
        "effective_fps": 3
      }
    ],
    "total": 3
  }
}

Question and answer

Question: Does the video stutter anywhere? When does it start?
Answer: The tool reports the picture repeats from 6.20 s, so the video stutters from there.

Tool returned: 6.2
Truth: 3.3

Check failedanswer 6.2, expected 3.3 ±0.1

How it was checked

Truth from: constructed
Fixed at: 2026-10-30 20:10

Planted by this recipe: ffmpeg kept the first 12 s of the source at 10/1 frames per second and held every second frame from frame 32 to frame 41 (1 s, 5 held frames), so each held slot repeats the frame before it. The picture first stops moving at 3.300 s; the tolerance 0.1 s allows the tool's range to start one frame early.

The script held every other frame for 1 s from 3.30 s, so the answer is that planted stutter, and the card does not test single dropped frames.

Try it yourself

Use agentic-video to check my video for stutter. Run check_frame_cadence on my file, then tell me where the picture repeats and the start and end time of each range. Use my own file.

Get the .mcpb file and open it in Claude Desktop.
Or: pip install agentic-video

Clip and licence

Licence: owner-made

Generated for the gallery; no third-party material.