Video Clip Extractor

What it does

When your agent uses it

• User needs to: extract highlights from long videos
• Cut best moments from videos
• Cut video highlights
• Process Bilibili/YouTube URLs

Example prompts

• “Use the video-clip-extractor skill to process videos to identify engaging moments, generate transcripts, and create highlight clips with artistic…”
• “/video-clip-extractor”

Requirements

• Python 3
• A credential in QWEN_API_KEY
• A credential in OPENROUTER_API_KEY
• Pre-approved tools (allowed-tools): Bash(uv run python video_orchestrator.py*), Bash(git clone*), Bash(git -C*openclip*), Bash(cd ~/.local/share/openclip*), AskUserQuestion

Workflow steps

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

1. 1Get the source — if the user didn't provide a video URL or file path, ask for it.
2. 2Clarify intent (optional) — if the user wants clips focused on a specific topic, capture it for --user-intent. If unclear, ask: "Any…
3. 3Check environment — does video_orchestrator.py exist in the current directory? If yes, run directly. Otherwise use the global install at…
4. 4Verify prerequisites — check ffmpeg is installed and at least one API key is set. Warn if missing before running.
5. 5Run the command and stream output to user.
6. 6Report results — after completion, list the generated clips with timestamps and titles.

What it can do on your machine

Read from SKILL.md and the folder at commit 0289627. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(uv run python video_orchestrator.py*)
  • Bash(git clone*)
  • Bash(git -C*openclip*)
  • Bash(cd ~/.local/share/openclip*)
  • AskUserQuestion

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv
  • brew
  • git
  • apt
  • pip

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

• Network

  Links to these hosts (documentation or services it may open):

  • ffmpeg.org

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • QWEN_API_KEY
  • OPENROUTER_API_KEY
  • GLM_API_KEY
  • MINIMAX_API_KEY
  • HUGGINGFACE_TOKEN

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

Context cost

Video Clip Extractor loads about 2.8k tokens when it runs. Until then it costs about 178 tokens; SKILL.md has 1,056 words of instructions outside code blocks.

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

~178

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

~2.8k

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

• NoteRuns commands with sudoSKILL.md:63

  - Ubuntu: `sudo apt install ffmpeg`

• WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:87

  | `--browser <browser>` | `firefox` | Browser for cookies: `chrome`, `firefox`, `edge`, `safari` |

• NoteRuns commands with sudoSKILL.md:192

  fmpeg: `brew install ffmpeg` (macOS) or `sudo apt install ffmpeg` (Ubuntu) |

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 linzzzzzz/openclip at commit 0289627, republished under its MIT licence (© linzzzzzz). 1,056 words, ~2,762 tokens.

name

video-clip-extractor

description

Processes videos to identify engaging moments, generate transcripts, and create highlight clips with artistic titles and custom cover images. Use when user needs to: extract highlights from long videos or livestreams, clip or cut best moments from videos, cut video highlights, process Bilibili/YouTube URLs or local video files, generate transcripts via Whisper, analyze content for engaging moments, create short-form clips with styled titles and covers, adjust cover text position and colors, find and export memorable scenes from recordings, burn subtitles into clips (with optional translation), guide clip selection with user intent, or identify speakers in multi-person conversations.

allowed-tools

Bash(uv run python video_orchestrator.py*), Bash(git clone*), Bash(git -C*openclip*), Bash(cd ~/.local/share/openclip*), AskUserQuestion

git clone https://github.com/linzzzzzz/openclip.git ~/.local/share/openclip
cd ~/.local/share/openclip && uv sync

git -C ~/.local/share/openclip pull && cd ~/.local/share/openclip && uv sync

uv run python video_orchestrator.py [options] <source>

cd ~/.local/share/openclip && uv run python video_orchestrator.py -o "$OLDPWD/processed_videos" [options] <source>

✅ Processing complete — 5 clips generated
📁 processed_videos/video_name/clips/

  clip_01.mp4  [00:12:34 – 00:15:20]  "Title of the moment"
  clip_02.mp4  [00:28:45 – 00:31:10]  "Another highlight"
  clip_03.mp4  [00:45:00 – 00:47:30]  "Key discussion point"
  ...

Cover images: clips/*.jpg

processed_videos/{video_name}/
├── downloads/              # Original video, subtitles, and metadata (URL sources)
├── local_videos/           # Copied video and subtitles (local file sources)
├── splits/                 # Split parts and AI analysis results
├── clips/                  # Generated highlight clips + cover images
└── clips_post_processed/   # Post-processed clips when using --add-titles and/or --burn-subtitles

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

Files

Just SKILL.md in .trae/skills/video-clip-extractor of linzzzzzz/openclip.

Open the folder on GitHubat commit 0289627