embed-subtitles
Burn subtitles onto videos using FFmpeg. Use for: hardcode subtitles, embed captions, video subtitling.
What this skill does
# Embed Subtitles
Burn SRT subtitles into video files using FFmpeg.
## Prerequisites
**No SRT file?** Use the `transcribe` skill first to generate subtitles from audio/video.
**Need translation?** After transcribing, read the SRT, translate each entry preserving timestamps, write new SRT file. No API needed.
## Quick Start
```bash
cd ~/.claude/skills/embed-subtitles/scripts
# Burn SRT into video
npx ts-node embed-subtitles.ts -i video.mp4 -s subtitles.srt -o output.mp4
# Custom styling
npx ts-node embed-subtitles.ts -i video.mp4 -s subtitles.srt -o output.mp4 \
--font-size 24 --position bottom --margin 40
# Add credit text overlay at end
npx ts-node embed-subtitles.ts -i video.mp4 -s subtitles.srt -o output.mp4 \
--credit "Your Name" --credit-position top
```
## Options
| Option | Short | Default | Description |
|--------|-------|---------|-------------|
| `--input` | `-i` | (required) | Input video file |
| `--subtitles` | `-s` | (required) | SRT subtitle file |
| `--output` | `-o` | (required) | Output video file |
| `--font-size` | | 20 | Font size in pixels |
| `--font-name` | | Arial | Font family name |
| `--position` | | bottom | Subtitle position: top, center, bottom |
| `--margin` | | 25 | Margin from edge in pixels |
| `--color` | | white | Text color |
| `--outline` | | 2 | Outline thickness |
| `--shadow` | | 1 | Shadow depth |
| `--credit` | | | Credit text to show at end |
| `--credit-position` | | top | Credit position: top, bottom |
| `--credit-duration` | | 2.5 | Credit display duration in seconds |
| `--extract-frame` | | | Extract frame at specified second for verification |
## Position Values
- `top` - Near top of video (good for credits, avoids bottom burned-in text)
- `center` - Middle of video
- `bottom` - Near bottom of video (traditional subtitle position)
## Dependencies
- FFmpeg (must be installed and in PATH)
## RTL Auto-Detection & Fix (CRITICAL)
**Before embedding ANY SRT file, Claude MUST check if the content is RTL.**
### Detection
Read the SRT file and check if the majority of text lines contain Hebrew/Arabic/Farsi characters:
- Hebrew range: `\u0590-\u05FF`
- Arabic range: `\u0600-\u06FF`
- Farsi additional: `\u0750-\u077F`
If RTL content is detected, apply the fix BEFORE passing to FFmpeg.
### RTL Fix
Wrap each text line (not index numbers, not timestamps) with Unicode directional marks:
```python
python3 -c "
import re
with open('SRT_FILE_PATH', 'r', encoding='utf-8') as f:
content = f.read()
lines = content.split('\n')
result = []
for line in lines:
stripped = line.strip()
if stripped and not re.match(r'^\d+$', stripped) and not re.match(r'\d{2}:\d{2}:\d{2}', stripped):
line = '\u202B' + line + '\u202C'
result.append(line)
with open('SRT_FILE_PATH', 'w', encoding='utf-8') as f:
f.write('\n'.join(result))
"
```
- **U+202B** (RLE - Right-to-Left Embedding): forces RTL paragraph direction
- **U+202C** (PDF - Pop Directional Formatting): closes the embedding
**This fixes:** English words at line start, periods/commas on wrong side, mixed bidi text.
### When to apply
Claude should analyze the SRT content intelligently:
- If most text is Hebrew/Arabic/Farsi → apply RTL fix
- If mixed but predominantly RTL → apply RTL fix
- If LTR (English, Spanish, etc.) → skip
- No flag needed from the user - detect automatically
## Notes
- For Arabic credits, use English text due to FFmpeg drawtext RTL limitations
- Use `--extract-frame` to verify subtitle positioning before final render
Related in Image & Video
watch
IncludedWatch 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.
physical-ai-defect-image-generation
IncludedUse 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.
accelint-react-best-practices
IncludedReact 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.
elevenlabs-agents
IncludedBuild 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
humanizer
IncludedHumanize 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.
generating-mermaid-diagrams
IncludedSalesforce 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.