video-audit
This skill should be used when the user asks to "audit this video", "analyze video quality", "check this video file", "is this video good quality", "should I reencode this", "what format is this video", or wants to understand a video file's technical properties and quality before working with it.
What this skill does
# Video File Audit
Analyze video files to understand their technical properties, identify quality issues, and recommend appropriate next steps (remux, reencode, or leave unchanged).
## Prerequisites
Requires `mediainfo` CLI tool. Install via:
- macOS: `brew install mediainfo`
- Linux: `apt install mediainfo` or equivalent
- Windows: Download from mediaarea.net
## Audit Workflow
### Step 1: Gather File Metadata
Run MediaInfo to get comprehensive file information:
```bash
mediainfo --Full "/path/to/video.mkv"
```
For quick summary:
```bash
mediainfo "/path/to/video.mkv"
```
### Step 2: Identify Container vs Codec
Extract and report separately:
**Container format** (file extension): mkv, mp4, webm, avi, mov, m2ts
- Containers store and package video/audio streams
- Changing container = remuxing (fast, lossless)
**Video codec** (actual encoding): H.264 (AVC), H.265 (HEVC), VP9, AV1, ProRes
- Codecs compress and encode the actual video data
- Changing codec = reencoding (slow, quality loss)
Key MediaInfo fields:
- `Format` under "General" section = container
- `Format` under "Video" section = codec
### Step 3: Check Color Space Parameters
Examine these fields in MediaInfo's Video section:
| Parameter | Expected Value | Problem Indicator |
|-----------|---------------|-------------------|
| Color primaries | BT.709 | BT.601 on HD content |
| Matrix coefficients | BT.709 | BT.601 on HD content |
| Transfer characteristics | BT.709 | Mismatched values |
| Color range | Limited | "Full" on broadcast content |
| Chroma subsampling | 4:2:0 | Unusual values |
**Red flags:**
- HD video (720p+) tagged as BT.601 instead of BT.709
- Mismatched matrix/primaries/transfer values
- "Full" range on content that should be "Limited"
For detailed color space information, consult `${CLAUDE_PLUGIN_ROOT}/references/color-space.md`.
### Step 4: Identify Quality Red Flags
Check MediaInfo for these warning signs:
**Encoding quality indicators:**
- `Encoded_Library`: Look for x264/x265 (good) vs NVENC/QuickSync (lower quality for archival)
- `Writing application`: Identify source (ffmpeg, Handbrake, etc.)
- `Bit rate mode`: VBR preferred over CBR for quality
**Suspicious characteristics:**
- Resolution not matching source (e.g., 4K from 1080p source = upscaled)
- Frame rate interpolated (e.g., 60fps from 24fps source)
- Very high or very low bitrate for resolution
- 10-bit encoding of 8-bit source content (acceptable, often more efficient)
**Content red flags:**
- HDR metadata on content never released in HDR (fake HDR)
- Dolby Vision on SDR-only content
- Unusual aspect ratios suggesting cropping or stretching
### Step 5: Provide Recommendations
Based on findings, recommend one of:
**Leave unchanged** when:
- Container and codec match intended use
- Color space parameters are correct
- No quality red flags detected
- File works with target application/device
**Remux only** when:
- Need different container (e.g., mkv→mp4 for compatibility)
- Container change doesn't require reencoding
- Color space just needs retagging (not conversion)
**Reencode required** when:
- Codec incompatible with target device
- Source has fixable quality issues (wrong matrix applied, not just mistagged)
- File size reduction needed (with quality tradeoff warning)
**Avoid/warn** when:
- Video already heavily compressed (reencoding will compound quality loss)
- User wants to upscale resolution (quality loss, not gain)
- User wants to interpolate frame rate (quality loss)
## Quick Reference: Container vs Codec
| If user says... | They probably mean... | Actual operation |
|-----------------|----------------------|------------------|
| "Convert mkv to mp4" | Change container | Remux (fast, lossless) |
| "Compress this video" | Reduce file size | Reencode (slow, quality loss) |
| "Make it H.265" | Change codec | Reencode (slow, quality loss) |
| "Fix the colors" | Depends on issue | Retag (fast) or reencode (slow) |
## Additional Resources
### Reference Files
For detailed technical information, consult:
- **`${CLAUDE_PLUGIN_ROOT}/references/quality-myths.md`** - Why resolution/bitrate don't equal quality
- **`${CLAUDE_PLUGIN_ROOT}/references/color-space.md`** - Color matrices, range, chroma location
- **`${CLAUDE_PLUGIN_ROOT}/references/tools.md`** - Recommended and discouraged tools
- **`${CLAUDE_PLUGIN_ROOT}/references/encoding-commands.md`** - ffmpeg/mpv command templates
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.