raw-video-processing
Post-process raw screen recordings by removing silent segments and applying speed adjustments. Uses FFmpeg-based Python scripts to optimize video pacing automatically.
What this skill does
# Skill: Raw Video Processing Post-process raw screen recordings to improve pacing — remove silent segments, then speed up the result. > **Prerequisite**: FFmpeg and uv must be installed. --- ## When to Use The user has recorded a screencast and wants to clean it up before publishing. Typical issues in raw recordings: - Long pauses / dead air while thinking or waiting for loading - Keyboard typing sounds and other low-level background noise that should be treated as silence - Overall pacing feels slow and could benefit from a slight speed boost --- ## Default Workflow When the user provides a raw video file, **run both scripts in sequence** by default: ### Step 1: Remove Silent Segments ```bash uv run --python 3.12 /path/to/skills/raw-video-processing/scripts/remove_silence.py <input.mp4> -t="-20dB" -d 0.5 ``` This detects and cuts out silent portions (including keyboard sounds), producing `<input>_nosilence.mp4`. **Always pass these parameters** (tuned for screen recordings with keyboard noise): - `-t="-20dB"` — aggressive threshold that filters out keyboard typing and background noise (use `=` syntax to avoid argparse treating negative values as flags) - `-d 0.5` — remove short silences too (0.5s minimum) - `-p 0.2` — seconds of breathing room kept around speech boundaries (default, usually no need to pass) The script prints a detailed summary: number of silent segments found, total silence removed, and all kept segments with timestamps. Review this output to confirm the result looks reasonable. ### Step 2: Speed Up the Video ```bash uv run --python 3.12 /path/to/skills/raw-video-processing/scripts/speed_video.py <input>_nosilence.mp4 ``` This applies a speed multiplier to the silence-removed video, producing `<input>_nosilence_1.2x.mp4`. **Default parameters**: - `--speed 1.2` — 1.2x playback speed (a subtle boost that doesn't feel rushed) --- ## Script Options ### remove_silence.py | Flag | Default | Description | |------|---------|-------------| | `-o`, `--output` | `<input>_nosilence.mp4` | Custom output path | | `-t`, `--threshold` | `-30dB` | Silence threshold in dB (higher = more aggressive). **Always use `-20dB` for screencasts** — pass as `-t="-20dB"` to avoid argparse issues with negative values | | `-d`, `--duration` | `0.8` | Minimum silence duration in seconds to remove. **Use `0.5` for screencasts** | | `-p`, `--padding` | `0.2` | Padding kept around non-silent segments | | `--dry-run` | off | Only print detected segments, don't export | ### speed_video.py | Flag | Default | Description | |------|---------|-------------| | `-o`, `--output` | `<input>_<speed>x.mp4` | Custom output path | | `-s`, `--speed` | `1.2` | Playback speed multiplier | --- ## Custom Scenarios - **Only remove silence** — run just Step 1. - **Only speed up** — run just Step 2 directly on the input file. - **Conservative cleanup** — use `-t="-30dB" -d 0.8` if the default is cutting too much speech. - **Extra aggressive cleanup** — use `-t="-15dB" -d 0.3` and `--speed 1.5` for maximum compression. - **Preview before committing** — use `--dry-run` on remove_silence.py to see what would be cut without creating a file. - **Custom output name** — use `-o` on either script to control the output path. --- ## Important Notes - Always run remove_silence **before** speed_video. Silence detection works on the original audio; speeding up first would alter the audio characteristics and make silence detection less accurate. - For long videos (>30 min), the silence removal step may take a few minutes as it processes each segment individually. - Both scripts preserve video quality — remove_silence uses stream copy (no re-encoding), while speed_video re-encodes with FFmpeg defaults.
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.