Extract frames or short clips from videos using ffmpeg.
NewMaintained
Automatic
◆Coding pack
Last verified 8/20/2026
What it changes
Passed 21 of 22 test cases with the skill, and 21 of 22 without it.
Without skill95%
With skill95%
Checks it passed that the model alone missed
Includes the -vframes 1 flag
1 fixed20 passed either way0 still failing1 broke
Pass-rate lift
0 pp
Tokens
+6%
Agent turns
0%
Response time
-26%
Model gemini-3.6-flashMeasured 8/20/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
Provide the shell command to grab just the very first image from `source.avi` and save it as `cover.jpg`.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses ffmpeg
Passed
Passed
Includes the -vframes 1 flag
Missed
Passed
case-03 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 lines2 filesincludes scripts
Video-frames
Purpose
Extract frames or short clips from videos using ffmpeg.
Routing
Use when: Use when the user asks to extract frames or short clips from videos using ffmpeg.
Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Outputs: Outcome from Video-frames: task-specific result plus concrete action notes.
Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.
Trigger Examples
Positive
Use the video-frames skill for this request.
Help me with video-frames.
Use when the user asks to extract frames or short clips from videos using ffmpeg.
Video-frames: provide an actionable result.
Negative
Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead.
Do not use video-frames for unrelated requests.
This request is outside video-frames scope.
This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
Current runtime prompt length: 462 characters.
Runtime prompt is defined directly in ../video-frames.json.