Video Clip Extractor
This is a full pipeline for turning long videos into shareable clips. Point it at a YouTube or Bilibili URL (or local file), and it transcribes with Whisper, runs LLM analysis to score engaging moments, then cuts highlights with ffmpeg. You get clips with custom cover images and optional artistic title overlays in ten different styles. The user intent flag lets you steer what counts as interesting, like "funny moments" or "technical explanations." It handles speaker diarization if you provide reference audio, burns subtitles with optional translation, and splits long videos into segments for parallel processing. Worth knowing it needs ffmpeg and an API key for Qwen, OpenRouter, GLM, or Minimax. Good for anyone processing streams or lectures who wants more than random timestamps.
- GitHub stars
- 516
- last updated
- May 19, 2026
Install
$ npx -y skills add linzzzzzz/openclip --skill video-clip-extractor --agent claude-codeInstalls into .claude/skills of the current project.
Files
Video Clip Extractor Skill
Run the video orchestrator to process videos and extract engaging highlights.
When Triggered
- Get the source — if the user didn't provide a video URL or file path, ask for it.
- Clarify intent (optional) — if the user wants clips focused on a specific topic, capture it for
--user-intent. If unclear, ask: "Any specific topic or moments to focus on? (e.g. 'funny moments', 'key arguments')" - Check environment — does
video_orchestrator.pyexist in the current directory? If yes, run directly. Otherwise use the global install at~/.local/share/openclip. - Verify prerequisites — check ffmpeg is installed and at least one API key is set. Warn if missing before running.
- Run the command and stream output to user.
- Report results — after completion, list the generated clips with timestamps and titles.
Setup (first use only)
Before running, determine the execution context:
- Inside openclip repo — if
video_orchestrator.pyexists in the current directory, skip setup and run directly. - Global install — if
~/.local/share/openclipdoes not exist, run these steps:
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/linzzzzzz/openclip
- Categories
- Documentation, Automation & Workflows, Generative Media, Video & Audio Editing
- License
- MIT
- First seen
- Jun 11, 2026
Recommended
More Documentation
core-brainstormlukerenton/explore-claude-codeCollaborative brainstorming mode for thinking through problems, ideas, and features before planning. Use when the user wants to discuss, explore ideas, or think0skills.sh installs
mcp-buildermalob/nix-configGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when b0skills.sh installs
create-analyzermc-zuri/mineflayer-bedrockCreate a new packet analyzer for Minecraft Bedrock logs. Generates template code, provides documentation links, and guides testing workflow.0skills.sh installs
implementmertbuilds/skillsBuild a feature in an isolated worktrunk worktree, commit, and open a draft PR. Use whenever the user asks to implement, build, add, or fix something that touch0skills.sh installs
Check Inline Code Formattingnextflow-io/trainingReview inline code in markdown files for proper formatting and syntax highlighting. Check for missing backticks on CLI flags, filenames, and code elements. Veri0skills.sh installs
theme-factorynicepkg/ai-workflowToolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fo0skills.sh installs