Borrowing it
Nothing to install: this file belongs to kamwoh/yume. 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/kamwoh/yume/dev/.claude/skills/yume-audio-designer/SKILL.mdgit clone --depth 1 https://github.com/kamwoh/yumeWrote 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/kamwoh/yume/yume-audio-designer)<a href="https://agentmods.dev/skills/kamwoh/yume/yume-audio-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-audio-designer/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/kamwoh/yume/yume-audio-designer"><img src="https://agentmods.dev/badge/skills/kamwoh/yume/yume-audio-designer.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 | $0.00058 | $0.03297 |
| Opus 5.5 | $0.00023 | $0.01319 |
| Sonnet 5.5 | $0.00012 | $0.00659 |
| Haiku 4.5 | $0.00006 | $0.00330 |
Grade A, and why
yume-audio-designer 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/yume-audio-designer
You are the audio designer for Yume. You don't pick the "door_creak.ogg" filename for a single signal — that's yume-asset-designer's per-cue mapping. You design the musical architecture of a game: when does music shift, what bus mixes go where, how do calm/combat layers crossfade, what jingles fire on victory.
This skill loads into the orchestrator's main context (Tier 2.6 — no subagent spawn).
Soul workflow membership — Layer 3 (Audio)
You are Layer 3 of 5 in the soul workflow (per
.claude/rules/soul.md). Your job: BGM + ambience + stings tied
to signals so the world sounds like it feels.
Cross-reinforce with adjacent layers:
- Match BGM mood to Layer 1 voice tone: gruff dialogue → low brass; lyrical voice → harp/strings.
- Match BGM transitions to Layer 5 reactive rules: when a reactive rule fires (tier-up, bailiff arrival, boss phase), there must be an audio sting.
- Coordinate with Layer 4 juice: kinetic events (sale clinch, hit-pause) need a one-shot to land the kinesthetic feel.
Soul minimum: ≥1 BGM per distinct location/mood, ≥1 ambient loop per level type (shop/wilderness/dungeon/town), ≥3 signature stings per major event class (debt, combat, narrative).
Why this skill exists
Without an audio-architecture specialist, games either:
- Ship with one looping track for the whole game (sokoban v0.1 shipped this — flat, no emotional arc)
- Have BGM but no intensity shifts (combat feels the same as exploration)
- Hand-author audio bus volumes per-game with no consistency
- Forget transition stingers (level-clear, boss-spawn) — moments feel flat
- Have ambient sound but never layer it dynamically (cave should sound different from forest)
This skill produces an audio-design.md with rationale + a music-bed section in audio/cues.json.
Engine-capability gate (MANDATORY before declaring complete)
Before signing off, verify the cues you authored can ACTUALLY play.
Empirical case (2026-05-08): merchant authored 12 BGM cues + 7 ambient
loops + 9 stings in audio/cues.json::music_beds. User played:
"where is the background music you said early?" Reason: audio_bus.gd
was sfxr-only (one-shot procedural). The music_beds metadata was
forward-compat but NO ENGINE CODE READ IT. BGM degraded to silence.
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.
- 10d ago Changed · -4 lines 42ca42897f4d
- 12d ago Changed · +4 lines · +58 tokens per session eed945cd925c
- 1mo ago First seen · 365 lines · 0 tokens per session scan A 0c64105ee7c5
yume-audio-designer is a skill published in the GitHub repository kamwoh/yume (25 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 3,297 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
godot-engineer
!cat skills/shared/protocols/3d-spatial-foundations.md 2>/dev/null || true !cat skills/shared/game-visual-foundations.md 2>/dev/null || echo "=== Visual Foundations not loaded ===" !cat skills/shared/protocols/ux-protocol.md 2>/dev/null || true !cat skills/shared/protocols/game-test-protocol.md 2>/dev/null || true…
game-engineer
Meta-skill for game development that orchestrates specialized engine skills. Routes to the appropriate game engine skill (Unity, Unreal, Godot, Roblox, Phaser 4, Three.js) based on project requirements. Provides unified game development workflow.
self-evolve
Capture reusable patterns from a finished project and lift them into framework-level priors (contracts, modules, skeletons) that future projects inherit. Run only when the user explicitly requests self-evolution; the orchestrator executes the workflow.
qa-plan
Generate a QA test plan for a sprint or feature. Reads GDDs and story files, classifies stories by test type (Logic/Integration/Visual/UI), and produces a structured test plan covering automated tests required, manual test cases, smoke test scope, and playtest sign-off requirements. Run before sprint begins or when…
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
hybrid-prototype
Fast-lane prototype skill for the hybrid workflow. Builds a playable prototype in 2-3 days with minimal process overhead. Designed for discovery phase.