Audio Design

What it does

When your agent uses it

• The user mentions audio mixing
• Adaptive/dynamic music
• Syncing gameplay to the beat

Example prompts

• “/audio-design”

Requirements

• Compatibility (from SKILL.md): Engine-agnostic concepts. Pairs with godot-audio (AudioServer/buses), Unity AudioMixer, Wwise/FMOD; snippets in GDScript-like pseudocode.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Bus routing and dB gain
2. 2Ducking via sidechain (music dips under voice)
3. 3SFX variation (kill the "machine gun" repeat)
4. 4Beat-synced events (quantize to the music grid)

What it can do on your machine

Read from SKILL.md and the folder at commit eac84e0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are gdscript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Engine-agnostic concepts. Pairs with godot-audio (AudioServer/buses), Unity AudioMixer, Wwise/FMOD; snippets in GDScript-like pseudocode.

  From compatibility in the SKILL.md frontmatter.

Context cost

Audio Design loads about 1.8k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 562 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~93

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ukanwat/overtime at commit eac84e0, republished under its Apache-2.0 licence (© ukanwat). 562 words, ~1,760 tokens.

name

audio-design

description

Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization. Engine-neutral. Use when the user mentions audio mixing, audio buses, adaptive/dynamic music, ducking, SFX variation, music layers, or syncing gameplay to the beat.

compatibility

Engine-agnostic concepts. Pairs with godot-audio (AudioServer/buses), Unity AudioMixer, Wwise/FMOD; snippets in GDScript-like pseudocode.

license

Apache-2.0

metadata.engine

none

metadata.category

disciplines

metadata.difficulty

intermediate

# Route sounds to named buses; control GROUPS, not individual clips.
sfx_player.bus = "SFX"
music_player.bus = "Music"

# Map a 0..1 settings slider to decibels (linear_to_db), the perceptual unit.
func set_bus_volume(bus_name: String, slider01: float) -> void:
    var idx := AudioServer.get_bus_index(bus_name)
    var db := linear_to_db(clamp(slider01, 0.0001, 1.0))   # 0 -> silence, 1 -> 0 dB
    AudioServer.set_bus_volume_db(idx, db)
# RIGHT: slider -> dB via linear_to_db. WRONG: assigning slider01 straight as dB
# (a "0.5" would be only +0.5 dB — almost no change — and 0 would be 0 dB, full).

# A compressor on the MUSIC bus, keyed by the VOICE bus, lowers music while
# dialogue plays, then releases. This is "sidechain ducking".
# Setup (engine-specific): add a compressor effect to the Music bus and set its
# sidechain to the Voice bus. Then tune:
#   threshold: level on Voice that triggers ducking (e.g. -30 dB)
#   ratio:     how hard to duck (e.g. 8:1 for a clear dip)
#   attack:    fast (~10 ms) so music gets out of the way promptly
#   release:   slow (~300-500 ms) so it recovers smoothly, not pumping
# No-middleware alternative: tween the Music bus volume down on voice start and
# back up on voice end.
func duck_music(active: bool) -> void:
    var target_db := -12.0 if active else 0.0
    create_tween().tween_method(
        func(v): set_bus_volume_db("Music", v), current_music_db, target_db, 0.25)

# Randomize pitch slightly and pick from a sample pool so repeats feel organic.
func play_varied(samples: Array, bus := "SFX") -> void:
    var p := AudioStreamPlayer.new()
    p.stream = samples[randi() % samples.size()]   # rotate through several takes
    p.bus = bus
    p.pitch_scale = randf_range(0.94, 1.06)         # +/- ~6% pitch wobble
    add_child(p); p.play()
    p.finished.connect(p.queue_free)                # clean up one-shots

# Schedule gameplay/visuals on musical time, not frame time, so they land on beat.
const BPM := 120.0
var seconds_per_beat := 60.0 / BPM

func current_beat(playback_position_sec: float) -> int:
    return int(playback_position_sec / seconds_per_beat)

# Quantize an action to the NEXT beat boundary instead of firing immediately.
func time_until_next_beat(pos: float) -> float:
    return seconds_per_beat - fmod(pos, seconds_per_beat)
# Drive timing from the audio playback clock, which is steadier than frame delta.

© ukanwat, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .claude/skills/audio-design of ukanwat/overtime.

• SKILL.md
• references/adaptive-music.md

Open the folder on GitHubat commit eac84e0

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ukanwat/overtime, which our catalogue first saw on October 7, 2026.

• gamedev-skills/awesome-gamedev-agent-skillsskills/disciplines/audio-design