semantic-video-clipper

Included with Lifetime

$97 forever

AI analyzes subtitles to identify optimal split points, then clips video segments using FFmpeg based on AI-provided cue indices. Use when asked to segment videos (e.g., .mp4) based on .vtt/.srt subtitles.

Image & Videoscripts

What this skill does


# Semantic Video Clipper

## Overview

Segment a long video into clips by having AI analyze subtitle semantics and identify natural topic boundaries. The lightweight Python script handles parsing, timing calculation, and FFmpeg clipping based on AI-provided segment indices. Output clips and matching subtitles with filenames `basename_<index>.*` in same directory as the source video.

## Workflow

### Step 1: AI Analysis
- Read full subtitle content (.vtt or .srt)
- Understand semantic flow and topic transitions
- Identify natural split points that:
  - Align with complete sentence endings
  - Occur at topic shifts (new concepts, examples, recaps)
  - Fit within duration constraints (typically 25-60 seconds)
- Return segment ranges as cue index pairs: `[(0, 12), (12, 25), (25, 40), ...]`

### Step 2: Python Script Execution
- Parse subtitles into Cue objects with timing
- Convert cue indices to time ranges
- Call FFmpeg in parallel to clip video segments
- Shift subtitle times so each segment starts at 00:00
- Save output files as `basename_1.mp4` + `basename_1.vtt`, `basename_2.*`, etc.

## Scripted execution

**Script location**: `skills/semantic-video-clipper/scripts/clip_video.py`

**Option 1: From skill directory** (recommended)

```bash
cd skills/semantic-video-clipper
python3 scripts/clip_video.py /path/video.mp4 /path/subtitles.vtt "0-12,12-25,25-40"
```

**Option 2: From any location**

```bash
python3 skills/semantic-video-clipper/scripts/clip_video.py /path/video.mp4 /path/subtitles.vtt "0-12,12-25,25-40"
```

The segments argument uses 0-based cue indices:
- `"0-12,12-25,25-40"` - Three segments: cues 0-11, 12-24, 25-39

Optional flags:

```bash
--workers 4          # Number of parallel workers (default: 4)
--dry-run            # Only print segment plan without clipping
```

## Dependencies

- `ffmpeg` (external - must be in PATH)

Notes:
- AI handles semantic analysis; Python script only handles parsing, timing, and FFmpeg clipping.
- Output files always land beside the source video, named with an underscore plus 1-based index.
- Parallel processing (`--workers`) provides 3-4x speedup for multi-clip videos.

Files: 2

Size: 11.8 KB

Complexity: 32/100

Category: Image & Video

Source: https://github.com/seefreed/skills/tree/main/semantic-video-clipper

Related in Image & Video

watch

Included

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.

Image & Videoscriptsfeatured

physical-ai-defect-image-generation

Included

Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.

Image & Videoscripts

accelint-react-best-practices

Included

React performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.

Image & Videoscripts

elevenlabs-agents

Included

Build conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication

Image & Videoscripts

humanizer

Included

Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.

Image & Videoscripts

generating-mermaid-diagrams

Included

Salesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.

Image & Videoscripts