Borrowing it
Nothing to install: this file belongs to ukanwat/aaabench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ukanwat/aaabench/main/.claude/skills/audio-design/SKILL.mdgit clone --depth 1 https://github.com/ukanwat/aaabenchWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ukanwat/aaabench/audio-design)<a href="https://agentmods.dev/skills/ukanwat/aaabench/audio-design"><img src="https://agentmods.dev/badge/skills/ukanwat/aaabench/audio-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ukanwat/aaabench/audio-design"><img src="https://agentmods.dev/badge/skills/ukanwat/aaabench/audio-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.01837 |
| Opus 5.5 | $0.00032 | $0.00735 |
| Sonnet 5.5 | $0.00016 | $0.00367 |
| Haiku 4.5 | $0.00008 | $0.00184 |
Grade A, and why
audio-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to audio-design — 135 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio design
Game audio is a mixing graph plus a music system. Route every sound through a
small set of buses so you can balance and process groups; make music react to
play through layering and re-sequencing rather than looping one track. This skill
teaches the portable practice; bind it to godot-audio, Unity's AudioMixer, or
middleware (FMOD/Wwise) for concrete APIs.
When to use
- Use to design a bus/mixer layout, set group volumes, and apply effects (reverb, compression, EQ) to groups of sounds.
- Use to duck music/ambience under dialogue or impacts (sidechain).
- Use to build adaptive music that responds to combat/exploration intensity.
- Use to add SFX variation (pitch/sample randomization) and sync events to a beat.
When not to use: for the engine's concrete audio nodes/streams, use
godot-audio or the engine's audio skill. Loading/streaming and asset import are
engine concerns. For UI sliders that drive bus volume, see the engine UI skill.
Core workflow
- Lay out buses, not per-sound volume. A typical tree:
Master ← {Music, SFX, Ambience, UI, Voice}. Everything plays into a bus; the player's settings sliders map to bus volumes. Never set hundreds of clip volumes by hand. - Work in decibels, not linear. Perceived loudness is logarithmic. Volume controls and automation should operate in dB; convert only at the edges.
- Leave headroom. Mix so the Master peaks below 0 dBFS (aim for a target loudness, e.g. around -14 to -16 LUFS for many games) to avoid clipping.
- Duck competing sources with a sidechain compressor (or volume automation): when voice/important SFX plays, the music bus dips, then recovers.
- Make music adaptive via vertical layering (stems faded in/out) and/or horizontal re-sequencing (swap segments at musical boundaries). See the reference.
- Vary repeated SFX with small random pitch/volume offsets and sample pools so footsteps and hits don't sound robotic.
- Verify on real output. Listen on headphones and speakers; check that the mix balances, ducking is audible but not pumping, and music transitions land on the beat — never assume from the editor meters alone.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 152 lines · 81 tokens per session scan A 85738d8ab967
audio-design is a skill published in the GitHub repository ukanwat/aaabench (385 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 1,837 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to audio-design, differing in 135 lines, and is treated as a copy.
Other skills, from other repositories
unreal-engineer
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || echo "=== 3D Foundations not loaded ===".
unreal-playtest-agent
Domain skill - run screenshot-light PIE playtest episodes with structured entity observations, bounded semantic actions, transition polling, and in-memory traces for QA and external policy or RL runners.
unreal-level
Domain skill - Unreal Engine level and world management: inspect level state, load and save maps, read or edit world settings, and measure native collision distances in Editor or PIE worlds. Not for individual actor transform edits - use unreal-actors for that.
unreal-pie
Domain skill - Unreal Engine Play-In-Editor (PIE) closed-loop verification. Provides PIE lifecycle control (enter/pause/resume/exit), controlled input injection (no OS dependency), viewport screenshot capture, output log snapshot, performance sampling, and Automation Test execution with async job polling. Use for…
unreal-actors
Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.
unreal-assets
Domain skill - Unreal Engine Content Browser asset management: list, import, export, inspect, and delete assets. Use for package and asset operations in the Unreal Editor. Not for actor placement or transforms - use unreal-actors for that.