video-cut
Skill210 starsChanged yesterdayMITView on GitHub
Cuts a single video at a specified time into two precisely timed MP4 segments using FFmpeg, defaulting to two equal-duration halves when no time is given. Re-encodes as compatible H.264/AAC so the cut is not shifted to a nearby keyframe. Use when the user wants to cut or divide a video into two parts, cut at a timestamp, split a video in half, or separate the first and second portions of a clip.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- godot-fun/godot-agentword for word, first seen Nov 15, 2026
- JamalMohafil/claude-skillstheir own version, first seen Nov 1, 2026
- WhiteTowerAI/cut-as-codetheir own version, first seen Oct 13, 2026
- yojuhsu/video-cuttheir own version, first seen Sep 1, 2026
- broomva/skillstheir own version, first seen Jun 13, 2026
Other versions5 projects use a version of this.
Word for word · 1
- godot-fun/godot-agent★ 210100% same
Edited · 0
None found.
Wrote their own version · 4
- JamalMohafil/claude-skills★ 27same name
- WhiteTowerAI/cut-as-code★ 16same name
- broomva/skills★ 4same name
- yojuhsu/video-cut★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/AGENTS.mdAGENTS.md
- ai-text-to-speechSkill
- audio-denoiseSkill
- audio-fadeSkill
- audio-loudness-normalizationSkill
- audio-sample-rate-standardizeSkill
- audio-splitSkill
- audio-to-oggSkill
- audio-to-textSkill
- audio-to-wavSkill
- audio-trimSkill
- audio-volume-adjustSkill
- file-naming-normalizationSkill
- git-commit-messageSkill
- image-inpaint-regionSkill
- image-region-remove-key-color-appSkill
- image-remove-backgroundSkill
- image-remove-white-backgroundSkill
- image-resizeSkill
- image-sprite-sheet-splitSkill
- image-to-pngSkill
- image-to-textSkill
- image-trimSkill
- storyboard-av-mixSkill
- storyboard-shot-to-htmlSkill
- storyboardSkill
- storyboard-ttsSkill
- video-4k-normalizationSkill
- video-bgmSkill
- video-compress-to-sizeSkill
- video-merge-gpuSkill
- video-mergeSkill
- video-publishSkill
- video-remove-audioSkill
- video-to-4kSkill
- video-to-60fpsSkill
- video-to-mp4Skill
- video-to-ogvSkill
- video-to-wavSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read and follow dependency-manager.
- Distinctive: line 29
Use one optional parameter:
- Very specific: line 44
Use -o / --output to choose an output directory.
- Distinctive: line 48
Use the bundled script, not handwritten FFmpeg commands.
- Distinctive: line 49
When the user asks for two halves without a timestamp, use the default 50% split.
- Distinctive: line 50
Do not use stream copy; it can move cuts to keyframes and produce unequal parts.
- Very specific: line 53
If Python or FFmpeg is missing, populate .dependency/ and retry.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Video Cut
Split one video into part 1 (start to split point) and part 2 (split point to end). Default to the exact temporal midpoint.
Rules
Read and follow dependency-manager. Run the bundled script as documented and install missing tools into .dependency/.
Quick Start
.dependency/python/python .ai/video-cut/cut.py --video path/to/video.mp4Outputs:
video-cut/video_part1.mp4
video-cut/video_part2.mp4Cut Point
Use one optional parameter:
| Flag | Meaning |
-s / --seconds | Cut position in seconds |
| none | Exact 50% midpoint |
.dependency/python/python .ai/video-cut/cut.py --video clip.mov --seconds 12.5Output
Encode both parts as H.264 CRF 18, preset medium, yuv420p, with AAC 192 kbps and faststart. Preserve source resolution and frame rate. Re-encoding provides frame-accurate cuts instead of keyframe-limited stream-copy cuts.
Use -o / --output to choose an output directory. Never overwrite or modify the source.
Agent Notes
- Use the bundled script, not handwritten FFmpeg commands.
- When the user asks for two halves without a timestamp, use the default 50% split.
- Do not use stream copy; it can move cuts to keyframes and produce unequal parts.
- Reject split points at zero or at/after the video duration.
- Tell the user both output paths.
- If Python or FFmpeg is missing, populate
.dependency/and retry. - See reference.md for the exact FFmpeg pipeline and cut behavior.
Tests
.dependency/python/python .ai/video-cut/test_cut.pyManual examples: cli/video-cut.md
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

