Team Audio

Before you start: read this whole install prompt, tell me in a few lines what this skill does and what installing it involves, and wait for my go-ahead before you do anything else. Prerequisites — INTEGRATED SYSTEM FIRST: this skill is one piece of the complete "Claude Code Game Studios" template (49 agents, 74 skills, studio templates and a studio CLAUDE.md, per the repository README). Each skill assumes that template is installed, with its conventions, its project.yaml / project.local.yaml configuration, its .claude/docs/ mode documents, its hooks (for example hooks/yaml-helper.sh, outside this skill's folder) and its .claude/scripts/ helpers. Installing this listing alone copies only this skill's folder, without the rest of the system: the skill may reference template agents, files, hooks or scripts that are absent outside the full template, and it may not run as designed on its own. No account, no key and no payment are needed to copy the files, and nothing is run during installation. Install "Team Audio" for me. The skill itself orchestrates the audio team for one feature or area through a gated pipeline; with no argument it prints usage and stops without spawning anything. It first resolves review_mode, automation and team.size by running the template's hooks/yaml-helper.sh, outside this skill's folder, and announces the active set before spawning anything: at the default team.size individual only the sound-designer runs, at small the audio-director, technical-artist and gameplay-programmer join, and at studio the accessibility-specialist and the primary engine specialist join too; an agent outside the active set is consulted through the nearest active core agent, never silently dropped. It reads the feature's design docs in design/gdd/ by section, the sound bible at design/audio/sound-bible.md (or the legacy design/gdd/sound-bible.md, recommending the move, and saying plainly when neither exists), the audio asset lists in assets/audio/ and any existing sound design docs. Step 1 spawns the audio-director for sonic identity, emotional tone, palette and adaptive-audio rules. Step 2 spawns the sound-designer (SFX specifications, audio events, mixing groups, ducking) and the accessibility-specialist in parallel: a gameplay-critical audio event with no visual cue or subtitle is BLOCKING, and Step 3 does not start until the user resolves it or explicitly accepts the gap. Step 3 spawns the technical-artist (audio middleware integration for Wwise, FMOD or native audio, bus structure, memory budgets, streaming strategy) and the primary engine specialist in parallel to validate the integration for the pinned engine; with no engine configured the specialist is skipped and the run records engine validation as NOT ASSESSED. Step 4 spawns the gameplay-programmer to implement or review the audio manager, wire audio events to gameplay triggers, implement adaptive music and occlusion/reverb zones, and write unit tests for audio event triggers. Sub-agents write their working artifacts under production/audio/[feature]/ (one file per agent: direction, SFX spec, accessibility, integration plan, engine notes) without a per-write prompt, under a bounded exception the file documents (the path is one the orchestrator named, the artifact is new under production/, docs/ or tests/, and the phase is gated by an AskUserQuestion decision point); implementation code is outside that exception and is written only after one ask for the whole file set. The orchestrator then compiles the audio design document itself and asks before writing design/audio/audio-[feature].md. Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/team-audio/ folder at the pinned commit: 1 file in total) Pinned version: install the code at commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418 exactly. Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Clone https://github.com/Donchitos/Claude-Code-Game-Studios into a temporary folder, check out commit 05ad7c8a5b8aa2aa86bbd3439ae7cf7295cac418, and copy the .claude/skills/team-audio/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - SKILL.md: SHA-256 ba6c237d4e63b25a397c06c967c7f98f7827db920237fd9be0170d3e0c59e4e3 If a file does not match, it changed since the listing was prepared: do not install it yet, tell me what you found and let me decide. 2. Read SKILL.md in full, and tell me in plain words: what the skill does when used, what it connects to, whether it reads or sends any personal information or credentials, and anything that seems unusual. Stop on any red flag and tell me before going further. Confirm these points from the files: - The skill folder holds 1 file: SKILL.md only. Nothing in the folder is a program; it is instructions the agent follows at use time. - Nothing is sent anywhere during installation itself; the only download at install time is the skill folder from GitHub at the pinned commit, and no project of mine is audited, read or modified. - Integrated-system reality, from the file: at use time the skill runs the template's hooks/yaml-helper.sh to resolve review_mode, automation and team.size, follows .claude/docs/automation-modes.md, config-resolution.md and error-recovery-protocol.md, reads my project's GDDs, sound bible and audio asset lists, and spawns template agents (sound-designer at every size; audio-director, technical-artist and gameplay-programmer at small and up; accessibility-specialist and the primary engine specialist at studio) — agents, docs and project files that live outside this skill's folder and are absent in a standalone install, so it cannot run as designed on its own. - At use time its sub-agents write new working artifacts under production/audio/[feature]/ without a per-write prompt, but only inside the bounded exception the file documents (orchestrator-named path, new artifact under production/, docs/ or tests/, phase gated by an AskUserQuestion); implementation code under the code root is written only after one ask for the whole file set, and the compiled design/audio/audio-[feature].md is written by the orchestrator itself only after its own "May I write" ask. No third-party service, account or credential is named in the file; Wwise and FMOD appear only as middleware options the technical-artist designs for, locally. - Do not design any audio, do not spawn any team agent, do not run any template hook, and do not use the skill in any way during this install: using it is a separate step that only starts when I ask for it later. 3. When I say "yes, install", install it as a skill: copy the whole team-audio folder into the agent's skills directory, in a folder named exactly "team-audio", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: team-audio), the 1 file in place with matching fingerprints. Do not run anything from the folder and do not use the skill to verify. 5. Report what was installed, where, and what I still need to do myself (for example: that it belongs to the full Claude Code Game Studios template and may not run standalone (it resolves its settings through the template's yaml-helper hook, reads the template's design/ and assets/ files and spawns its audio team agents), and that at use time its sub-agents write working artifacts under production/audio/ under a documented bounded exception, implementation code only after one ask for the set, and the compiled audio design only after the orchestrator's own write ask). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.