Game audio principles.
npx skills add https://github.com/Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI --skill game-audio
> Sound design and music integration for immersive game experiences.
| Category | Behavior | Examples |
|----------|----------|----------|
| Music | Looping, crossfade, ducking | BGM, combat music |
| SFX | One-shot, 3D positioned | Footsteps, impacts |
| Ambient | Looping, background layer | Wind, crowd, forest |
| UI | Immediate, non-3D | Button clicks, notifications |
| Voice | Priority, ducking trigger | Dialogue, announcer |
When sounds compete for channels:
1. Voice (highest - always audible)
2. Player SFX (feedback critical)
3. Enemy SFX (gameplay important)
4. Music (mood, but duckable)
5. Ambient (lowest - can drop)
| Approach | When to Use | Trade-offs |
|----------|-------------|------------|
| Recording | Realistic needs | High quality, time intensive |
| Synthesis | Sci-fi, retro, UI | Unique, requires skill |
| Library samples | Fast production | Common sounds, licensing |
| Layering | Complex sounds | Best results, more work |
| Layer | Purpose | Example: Gunshot |
|-------|---------|------------------|
| Attack | Initial transient | Click, snap |
| Body | Main character | Boom, blast |
| Tail | Decay, room | Reverb, echo |
| Sweetener | Special sauce | Shell casing, mechanical |
Game State → Music Response
│
├── Menu → Calm, loopable theme
├── Exploration → Ambient, atmospheric
├── Combat detected → Transition to tension
├── Combat engaged → Full battle music
├── Victory → Stinger + calm transition
├── Defeat → Somber stinger
└── Boss → Unique, multi-phase track
| Technique | Use When | Feel |
|-----------|----------|------|
| Crossfade | Smooth mood shift | Gradual |
| Stinger | Immediate event | Dramatic |
| Stem mixing | Dynamic intensity | Seamless |
| Beat-synced | Rhythmic gameplay | Musical |
| Queue point | Next natural break | Clean |
| Parameter | Affects | Example |
|-----------|---------|---------|
| Threat level | Music intensity | Enemy count |
| Health | Filter, reverb | Low health = muffled |
| Speed | Tempo, energy | Racing speed |
| Environment | Reverb, EQ | Cave vs outdoor |
| Time of day | Mood, volume | Night = quieter |
| System | What Changes | Best For |
|--------|--------------|----------|
| Vertical (layers) | Add/remove instrument layers | Intensity scaling |
| Horizontal (segments) | Different music sections | State changes |
| Combined | Both | AAA adaptive scores |
| Element | 3D Positioned? | Reason |
|---------|----------------|--------|
| Player footsteps | No (or subtle) | Always audible |
| Enemy footsteps | Yes | Directional awareness |
| Gunfire | Yes | Combat awareness |
| Music | No | Mood, non-diegetic |
| Ambient zone | Yes (area) | Environmental |
| UI sounds | No | Interface feedback |
| Distance | Sound Behavior |
|----------|----------------|
| Near | Full volume, full frequency |
| Medium | Volume falloff, high-freq rolloff |
| Far | Low volume, low-pass filter |
| Max | Silent or ambient hint |
| Platform | Recommended Format | Reason |
|----------|-------------------|--------|
| PC | OGG Vorbis, WAV | Quality, no licensing |
| Console | Platform-specific | Certification |
| Mobile | MP3, AAC | Size, compatibility |
| Web | WebM/Opus, MP3 fallback | Browser support |
| Game Type | Audio Budget | Strategy |
|-----------|--------------|----------|
| Mobile casual | 10-50 MB | Compressed, fewer variants |
| PC indie | 100-500 MB | Quality focus |
| AAA | 1+ GB | Full quality, many variants |
| Category | Relative Level | Notes |
|----------|----------------|-------|
| Voice | 0 dB (reference) | Always clear |
| Player SFX | -3 to -6 dB | Prominent but not harsh |
| Music | -6 to -12 dB | Foundation, ducks for voice |
| Enemy SFX | -6 to -9 dB | Important but not dominant |
| Ambient | -12 to -18 dB | Subtle background |
| When | Duck What | Amount |
|------|-----------|--------|
| Voice plays | Music, Ambient | -6 to -9 dB |
| Explosion | All except explosion | Brief duck |
| Menu open | Gameplay audio | -3 to -6 dB |
| Don't | Do |
|-------|-----|
| Play same sound repeatedly | Use variations (3-5 per sound) |
| Max volume everything | Use proper mix hierarchy |
| Ignore silence | Silence creates contrast |
| One music track loops forever | Provide variety, transitions |
| Skip audio in prototype | Placeholder audio matters |
> Remember: 50% of the game experience is audio. A muted game loses half its soul.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take dokhacgiakhoa/game-audio from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.