Video Merge

What it does

When your agent uses it

• The user wants video merge
• Concatenate videos
• Transition animation
• Batch stitch clips with transitions

Example prompts

• “Use the video-merge skill to merge multiple videos from a folder (sorted by filename) into one clip with a random xfade transition (0.5s) between…”
• “/video-merge”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Use the bundled script — do not hand-write ffmpeg xfade chains.
2. 2Transition duration is fixed at 0.5s — no duration override flag.
3. 3Every clip except the first must be longer than 0.5s (incoming side of xfade).
4. 4Single file in the folder → re-encode to the output spec with no transition.
5. 5Many clips (4K10) auto-chunk (max 4 inputs per filtergraph) to avoid OOM; transitions stay correct across chunk boundaries.
6. 6Missing Python/FFmpeg → populate .dependency/ per skill-dependency-manager, retry.
7. 7FFmpeg filter details: reference.md

What it can do on your machine

Read from SKILL.md and the folder at commit 6394686. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Merge loads about 904 tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~102

When it runs · the whole SKILL.md, loaded when a task matches

~904

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from godot-fun/gai at commit 6394686, republished under its MIT licence (© godot-fun). 336 words, ~904 tokens.

name

video-merge

description

Merges multiple videos from a folder (sorted by filename) into one clip with a random xfade transition (0.5s) between each pair; freeze-pads so total duration equals the sum of sources. Exports 3840×2160 60fps H.265 Main10 40Mbps + AAC 320kbps. Use when the user wants video merge, concatenate videos, video concat, transition animation, xfade, join clips, or batch stitch clips with transitions.

disable-model-invocation

true

.dependency/python/python .ai/video-merge/merge.py --folder path/to/clips

assets/shots/
  01.mp4
  02.mp4
  03.mp4
→ assets/shots/video-merge/shots.mp4

.dependency/python/python .ai/video-merge/merge.py --folder clips
.dependency/python/python .ai/video-merge/merge.py --folder clips -o out/final.mp4

.dependency/python/python .ai/video-merge/test_merge.py

© godot-fun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/video-merge of godot-fun/gai.

• SKILL.md
• reference.md

Open the folder on GitHubat commit 6394686