Create Architecture

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 "Create Architecture" for me. It is the Game Studios master-architecture author. SKILL.md is the orchestrator: each of its phases lives in its own file under references/ (0-load-context, 1-layers, 2-module-ownership, 3-data-flow, 4-api-boundaries, 5-adr-audit, 6-missing-adrs, 7-write, 8-handoff), read and followed in turn. It loads the pinned engine reference docs and every GDD's technical sections into a Technical Requirements Baseline whose TR-IDs stay stable against docs/architecture/tr-registry.yaml (new ones are provisional, numbered via the template's registry script), maps systems into layers, defines module ownership, data flow and API boundaries with an approval at each phase, audits existing ADRs against the baseline, lists the ADRs still missing, then writes docs/architecture/architecture.md once — in full review mode after a parallel technical-director sign-off (TD-ARCHITECTURE) and lead-programmer feasibility review (LP-FEASIBILITY), whose verdicts are recorded in the document's status block after their own ask. Focus arguments (layers, data-flow, api-boundaries, adr-audit) run a single phase and update just that section of an existing document. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/create-architecture/ folder at the pinned commit: 10 files 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/create-architecture/ 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 0613360ba1247bbfc53f840b0f97d15430f38799b4a67498c6efabe53763c23d - references/0-load-context.md: SHA-256 2083798d7784c597ca8b9c0933f13d3fd2161936c0fc6771a351f98ab0b56481 - references/1-layers.md: SHA-256 889231d49bd42e96bb0d4cd3bb052434bce83f5567ebf2d1567b82b3712a0f46 - references/2-module-ownership.md: SHA-256 1c373de52748ed4941a223092f6a6d17b251df32cac500f275672f4742ee5dff - references/3-data-flow.md: SHA-256 33664f68c24c751182df4a95eda3ae2740a94381d58a7806b1d2a40c2b96506a - references/4-api-boundaries.md: SHA-256 dc914d8fa14cb7e80b46fbc4702d327ba473284744425272f854237645f6d0fd - references/5-adr-audit.md: SHA-256 f2dffe08fe962b555cf87f62141cd82b12928ceb7fa67544f5a6c8f485b58e51 - references/6-missing-adrs.md: SHA-256 d88aa82cabb0803e6b8d989664da8b219eed7f8e39de7fe66b9c635aefdf1ade - references/7-write.md: SHA-256 e10e9fb89a6b09bd0cd41791d8da83dd79f996a83847982daccf144e0960ee69 - references/8-handoff.md: SHA-256 dd6f3eb676c4497cf61383cee696d94db1dc7d22c73d5baa574a1f215229bf77 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 10 files: SKILL.md, the orchestrator, plus 9 phase files under references/ (0-load-context, 1-layers, 2-module-ownership, 3-data-flow, 4-api-boundaries, 5-adr-audit, 6-missing-adrs, 7-write, 8-handoff) that the SKILL.md reads and follows phase by phase. Nothing in the folder is a program; the phase files are instructions the skill reads 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 read or modified. - Integrated-system reality, from the files: at use time the skill resolves studio configuration by running the template's hooks/yaml-helper.sh (keys review_mode, automation, workflow, docs.density), reads the template's .claude/docs/ director-gates, engine-reference and template documents, calls the template's .claude/scripts/registry.sh for TR-ID numbering, records approved decisions in production/session-state/active.md, and in full review mode spawns the template's technical-director and lead-programmer agents — files, scripts and agents that live outside this skill's folder and are absent in a standalone install, so parts of it cannot run outside the full template. Inside the template it works on my project's own GDDs, ADRs and engine docs, locally. - At use time it writes only in my own project and under the template's ask-before-writing protocol: approved decisions are recorded in production/session-state/active.md as phases advance, and the master document docs/architecture/architecture.md is written once, after every section is approved (an update writes only the chosen sections, after its own ask). No account, key, payment or third-party service is named in the files I read. - Do not author any architecture, do not run any template hook, script or agent, 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 create-architecture folder into the agent's skills directory, in a folder named exactly "create-architecture", keeping its 10 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: create-architecture), the 10 files 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, numbers requirements through the template's registry script and signs off through template director agents), and that inside the template it writes my master architecture document only after every section is approved). 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.