audio-production
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.
- Installs
- 290
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/travisjneuman/.claude --skill audio-production- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads audio-production automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Audio Production
Rendering, encoding, and audio or image synthesis run only on the owner's designated media host when the private layer defines one, in a dated work folder outside any repository; on other hosts, plan and write source only. Source logos are copy-only.
Comprehensive guide for professional audio production across music, podcasts, video, and interactive media.
Audio Fundamentals
The Audio Signal Chain
SOURCE → CAPTURE → PROCESS → OUTPUT
Detailed:
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐
│ Source │→→→│ Mic │→→→│ Preamp │→→→│Interface│
│(voice, │ │ │ │ │ │ (A/D) │
│ instr.) │ │ │ │ │ │ │
└─────────┘ └─────────┘ └─────────┘ └────┬────┘
│
▼
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐
│Speakers │←←←│ (D/A) │←←←│ Mix │←←←│ DAW │
│Headphone│ │Interface│ │ Master │ │Recording│
└─────────┘ └─────────┘ └─────────┘ └─────────┘
Key Audio Concepts
| Concept | Definition | Standard |
|---|---|---|
| Sample Rate | Samples per second | 44.1kHz, 48kHz, 96kHz |
| Bit Depth | Dynamic range resolution | 16-bit, 24-bit, 32-bit float |
| Bit Rate | Data per second (compressed) | 128-320 kbps (MP3) |
| Dynamic Range | Loudest to quietest | ~96dB (16-bit), ~144dB (24-bit) |
| Headroom | Space below 0 dBFS | -6 to -18 dB typical |
Frequency Spectrum
20 Hz 20,000 Hz
├───────────────────────────────────────────────────────┤
SUB-BASS │ BASS │ LOW-MID │ MID │ HIGH-MID │ HIGH
20-60 │ 60-250 │ 250-500 │500-2k │ 2k-6k │ 6k-20k
│ │ │ │ │
Rumble │ Warmth │ Body │ Pres- │ Presence │ Air
Feel │ Punch │ Muddiness│ ence │ Harshness│ Sibilance
Decibel Reference Points
dBFS (Full Scale):
0 dBFS ████████████ Digital maximum (clipping)
-3 dBFS ██████████ Peaks (leave headroom)
-6 dBFS █████████ Recommended peak ceiling
-12 dBFS ███████ Average loud signal
-18 dBFS ██████ Recommended recording level
-24 dBFS ████ Conservative level
-60 dBFS █ Noise floor target
Recording
Microphone Types
| Type | Principle | Best For |
|---|---|---|
| Dynamic | Moving coil | Loud sources, live, durable |
| Condenser | Capacitor | Studio vocals, acoustic, detail |
| Ribbon | Thin metal strip | Vintage tone, smooth highs |
| USB | Built-in ADC | Podcasts, convenience |
Polar Patterns
CARDIOID FIGURE-8 OMNI
╭─────╮ ╭───╮ ╭─────╮
╭─┤ ├─╮ ╭─┤ ├─╮ ╭─┤ ├─╮
│ │ │ │ │ │ │ │ │ │ │ │
│ │ ● │ │ │ │ ● │ │ │ │ ● │ │
│ │ │ │ │ │ │ │ │ │ │ │
╰─┤ ├─╯ ╰─┤ ├─╯ ╰─┤ ├─╯
╰─────╯ ╰───╯ ╰─────╯
Front pickup Front + Back All around
Recording Levels
Target Peaks: -12 to -6 dBFS
Average Level: -18 to -12 dBFS
Why?
- Leaves headroom for processing
- Matches analog equipment sweet spot
- Prevents digital clipping
- 24-bit has plenty of resolution
Recording Best Practices
- Set gain before recording (never during)
- Record at 24-bit minimum
- Use 48kHz for video, 44.1kHz for music
- Monitor with headphones
- Record a few seconds of room tone
- Check phase when using multiple mics
- Label takes immediately
Essential Processing
EQ (Equalization)
Types:
- High-pass filter (HPF): Removes low frequencies
- Low-pass filter (LPF): Removes high frequencies
- Bell/Peak: Boost or cut specific frequency
- Shelf: Boost or cut above/below frequency
Common Applications:
┌─────────────────────────────────────────┐
│ Vocal: │
│ HPF at 80-100Hz (remove rumble) │
│ Cut 200-300Hz (reduce mud) │
│ Boost 3-5kHz (presence) │
│ Shelf boost 10kHz+ (air) │
├─────────────────────────────────────────┤
│ Kick Drum: │
│ Boost 50-80Hz (sub) │
│ Cut 300-400Hz (boxiness) │
│ Boost 3-5kHz (attack/click) │
├─────────────────────────────────────────┤
│ Electric Guitar: │
│ HPF at 80Hz │
│ Cut 400-600Hz if muddy │
│ Boost 2-4kHz (bite) │
└─────────────────────────────────────────┘
Compression
Parameters:
┌────────────────────────────────────────────────┐
│ Threshold: Level where compression starts │
│ Ratio: Amount of compression (4:1, 8:1, etc.) │
│ Attack: Time to engage (fast=punch, slow=body)│
│ Release: Time to disengage │
│ Knee: Hard (sudden) or soft (gradual) │
│ Makeup Gain: Restore lost volume │
└────────────────────────────────────────────────┘
Common Settings:
┌─────────────────────────────────────────┐
│ Vocals: 3:1-4:1, medium attack/release │
│ Drums: 4:1-8:1, fast attack │
│ Bass: 4:1, medium attack │
│ Mix Bus: 2:1-3:1, slow attack, 1-3dB GR│
└─────────────────────────────────────────┘
Reverb
| Type | Character | Use |
|---|---|---|
| Room | Small, tight | Natural ambience |
| Hall | Large, spacious | Orchestral, ballads |
| Plate | Bright, smooth | Vocals, snare |
| Spring | Vintage, boingy | Guitar, lo-fi |
| Chamber | Warm, dense | Natural depth |
Key Parameters:
- Pre-delay: Time before reverb (50-100ms for vocals)
- Decay/RT60: How long it lasts
- Damping: High-frequency absorption
- Size: Room dimensions
- Mix/Wet-Dry: Balance with original
Delay
| Type | Application |
|---|---|
| Slapback | 50-150ms, rockabilly, presence |
| Stereo | Different L/R times, width |
| Ping-pong | Alternating L/R, interest |
| Tempo-sync | 1/4, 1/8 notes, rhythmic |
Mixing
Gain Staging
Signal Flow Levels:
┌─────────────────────────────────────────┐
│ Input: -18 dBFS (sweet spot) │
│ ↓ │
│ Plugin 1: Output matches input level │
│ ↓ │
│ Plugin 2: Output matches input level │
│ ↓ │
│ Fader: Unity (0 dB) ideally │
│ ↓ │
│ Bus: -12 to -6 dBFS peaks │
│ ↓ │
│ Master: -6 dBFS peaks (before limit) │
└─────────────────────────────────────────┘
Panning Guidelines
Stereo Field:
Hard L L L-C CENTER R-C R Hard R
│ │ │ │ │ │ │
│ │ │ │ │ │ │
Rhythm Gtr1 Keys1 Vocal Keys2 Gtr2 Rhythm
Gtr BVox1 Bass BVox2 Gtr
Kick
Snare
Common Positions:
- Center (0): Lead vocal, bass, kick, snare
- Slight L/R: Main instruments, harmonies
- Wide L/R: Rhythm guitars, stereo keys
- Hard L/R: Doubled parts, effects
Frequency Balancing
Making space (subtractive EQ approach):
┌────────────────────────────────────────────┐
│ Kick: Boost 60Hz │ Cut from Bass here │
│ Bass: Boost 80-100 │ Cut from Kick here │
│ Gtr: Owns 1-3kHz │ Cut vocal slightly │
│ Vocal: Boost 3-5kHz │ Cut guitar slightly │
└────────────────────────────────────────────┘
Each element should have its own frequency "home"
Mix Bus Processing
Typical Chain:
1. Subtle EQ (tonal shaping)
2. Light compression (2:1, 1-3dB GR)
3. Stereo enhancement (if needed)
4. Limiter (only for reference bounce)
Keep mix bus processing minimal!
Leave headroom for mastering.
Mastering
Mastering Goals
- Tonal Balance: Even frequency response
- Dynamics: Appropriate loudness/dynamics
- Stereo Image: Width and mono compatibility
- Translation: Sounds good everywhere
- Format: Prepare for distribution
Loudness Standards
| Platform | Target | Measurement |
|---|---|---|
| Spotify | -14 LUFS | Integrated |
| Apple Music | -16 LUFS | Integrated |
| YouTube | -14 LUFS | Integrated |
| Broadcast (US) | -24 LUFS | Integrated |
| Broadcast (EU) | -23 LUFS | Integrated |
| CD | -9 to -12 LUFS | Integrated |
Mastering Chain (Typical)
1. Reference Import
└─→ Compare to commercial releases
2. EQ (Linear Phase)
└─→ Broad adjustments only
3. Multiband Compression
└─→ Control specific bands
4. Stereo Width
└─→ Enhance or narrow
5. Limiting
└─→ Final loudness, prevent clipping
6. Dither (if needed)
└─→ 16-bit conversion only
Podcast Production
Recording Setup
Recommended Signal Chain:
Mic → Audio Interface → DAW
Equipment Tiers:
┌─────────────────────────────────────────┐
│ Budget: USB Mic (Blue Yeti, AT2020) │
│ Mid: SM7B + Cloudlifter + Interface│
│ Pro: Large diaphragm condenser │
│ + high-end preamp │
└─────────────────────────────────────────┘
Podcast Processing Chain
1. Noise Reduction
└─→ Remove room noise, hum
2. De-essing
└─→ Tame harsh "s" sounds
3. Compression
└─→ Even out volume (3:1-4:1)
4. EQ
└─→ HPF at 80Hz, presence boost
5. Limiter
└─→ Catch peaks, -1 dBFS ceiling
Target: -16 LUFS (mono), -19 LUFS (stereo)
True Peak: -1 dBTP
Podcast Export Settings
Standard:
- Format: MP3 or AAC
- Bitrate: 128 kbps (mono), 192 kbps (stereo)
- Sample rate: 44.1 kHz
High Quality:
- Format: AAC
- Bitrate: 256 kbps
- Sample rate: 48 kHz
Chapters: Use ID3 tags for chapter markers
Artwork: 3000x3000 minimum, JPG or PNG
Sound Design
Creating Sounds
Approaches:
1. Recording: Capture real sounds (foley)
2. Synthesis: Create from oscillators
3. Sampling: Manipulate existing sounds
4. Processing: Transform through effects
5. Layering: Combine multiple sources
Synthesis Types
| Type | Method | Sound Character |
|---|---|---|
| Subtractive | Filter oscillators | Classic analog |
| FM | Frequency modulation | Metallic, bells |
| Wavetable | Morphing waveforms | Modern, evolving |
| Granular | Tiny sound particles | Texture, pads |
| Additive | Stack sine waves | Precise, organs |
| Physical Modeling | Simulate physics | Realistic instruments |
Layering Formula
Sound Design Stack:
┌─────────────────────────────────────┐
│ TOP: High frequencies (air, presence)│
│ MID: Character, tone │
│ LOW: Foundation, weight │
│ SUB: Felt, not heard (20-60Hz) │
│ TRANSIENT: Attack, punch │
└─────────────────────────────────────┘
Process each layer separately, combine at end.
DAWs (Digital Audio Workstations)
| DAW | Strengths | Platform |
|---|---|---|
| Pro Tools | Industry standard, editing | All |
| Logic Pro | Complete package, Apple | macOS |
| Ableton Live | Live performance, electronic | All |
| FL Studio | Beat making, workflow | All |
| Reaper | Customizable, affordable | All |
| Cubase | MIDI, composition | All |
| Studio One | Modern workflow | All |
| Audacity | Free, simple editing | All |
File Formats
| Format | Type | Quality | Use |
|---|---|---|---|
| WAV | Uncompressed | Lossless | Production, archive |
| AIFF | Uncompressed | Lossless | Mac production |
| FLAC | Compressed | Lossless | Archive, audiophile |
| ALAC | Compressed | Lossless | Apple ecosystem |
| MP3 | Compressed | Lossy | Distribution |
| AAC | Compressed | Lossy | Streaming, Apple |
| OGG | Compressed | Lossy | Games, open source |
Export Specifications
For Mastering:
- Format: WAV
- Bit depth: 24-bit (or 32-bit float)
- Sample rate: Match session (typically 44.1/48kHz)
- Headroom: -6 dBFS peaks
For Distribution:
- Format: WAV or FLAC (lossless)
- Bit depth: 16-bit (with dither)
- Sample rate: 44.1 kHz
- Loudness: Platform target LUFS
Best Practices
DO:
- Record at proper levels (-18 dBFS average)
- Use reference tracks
- Take breaks (ear fatigue is real)
- Check mono compatibility
- Use subtractive EQ first
- Process in series, not parallel (usually)
- Save project versions regularly
- Export stems for backup
DON'T:
- Record with processing (usually)
- Mix at high volumes
- Over-compress everything
- Solo instruments too long
- Trust only one playback system
- Rush the mixing process
- Forget to dither (16-bit only)
- Master your own mixes (ideally)
Quality Checklist
Pre-Export
- Gain staging correct throughout
- No clipping or distortion
- Phase issues resolved
- Mono compatibility checked
- Low-end translation verified
- High frequencies not harsh
Final Check
- Listen on multiple systems
- Check in car, phone, earbuds
- Verify format specifications
- Confirm LUFS target met
- True peak below -1 dBTP
- Metadata correctly embedded
FAQ
What does the audio-production skill do?
Professional audio production for music, podcasts, and sound design. Use when working with audio recording, mixing, mastering, or sound design for any medium.
How do I install audio-production?
Run npx skills add https://github.com/travisjneuman/.claude --skill audio-production in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/audio-production/ (personal) or .claude/skills/audio-production/ (project).
Which AI agents can use audio-production?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is audio-production safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains audio-production?
It is published by travisjneuman in travisjneuman/.claude. It has 290 recorded installs.
More from travisjneuman/.claude
document-skills
travisjneuman/.claude
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
brand-identity
travisjneuman/.claude
Brand strategy and identity design for businesses and products. Use when creating brand guidelines, developing visual identity systems, or defining brand positioning.
travel-planner
travisjneuman/.claude
Travel destination research and daily itinerary creation with logistics planning, budget tracking, and experience optimization. Use when planning trips, creating travel itineraries, comparing destinations, or organizing travel logistics.
business-strategy
travisjneuman/.claude
Business strategy expertise for strategic planning, competitive analysis, market entry, M&A strategy, portfolio management, and strategic decision-making. Use when analyzing competitive positioning, planning growth strategies, or making strategic decisions.
graphic-design
travisjneuman/.claude
Professional graphic design principles for digital and print media. Use when creating visual designs, choosing color palettes, typography, layouts, or providing design feedback.
real-estate-analyzer
travisjneuman/.claude
Open the skill to read its SKILL.md instructions.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image