Design System

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 "Design System" for me. It authors the game design document (GDD) for one system, section by section, cross-referencing its dependencies. The SKILL.md itself is a thin orchestrator: each of its five phases lives in its own file under references/ (1-parse-arguments, 2-gather-context, 3-file-skeleton, 4-section-design, 5-post-design), which the session reads and follows in turn. It gathers context first (game concept or, at the minimal tier, the one-page brief, the systems index, dependency GDDs and ADRs), asks before creating the GDD skeleton at design/gdd/[system-name].md with only the sections the resolved tier requires (8 at full, 5 at standard plus Formulas when the system defines numeric rules), then walks each section through a Context, Questions, Options, Decision, Draft, Approval, Write cycle — in collaborative mode it never writes a section without the user's approval, and each approved section is written immediately so an interrupted session can resume from production/session-state/active.md. Domain sections are routed to the template's specialist agents (game-designer, systems-designer, economy-designer, narrative-director and others by category), which return analysis only: the main session owns every file write, agents never write directly. Post-design, it self-checks the finished GDD, runs a creative-director pillar gate in full review mode, and asks separately before updating the entity registry (design/registry/entities.yaml, then validated with the template's .claude/scripts/registry.sh), the systems index and the session state. It never offers /design-review inline — the review must happen in a fresh session. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/design-system/ folder at the pinned commit: 6 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/design-system/ 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 9c4e7d1f1594e062c50f96e60a06d5a0fbaae1f90a7f4f9762f0952b7248d396 - references/1-parse-arguments.md: SHA-256 5a0ad57af5d5d3b4d225c6a81f1d21d5e6e709c723ab48d115829d2531175329 - references/2-gather-context.md: SHA-256 149f349250ed5c49c8fbe9cba92f4f1f750b9d5dce96c9a98267cfe29d8a0040 - references/3-file-skeleton.md: SHA-256 95dc956f90e443d15f4cd0ff4f7709f70c9068d5da5b163c9226220ac7d89e52 - references/4-section-design.md: SHA-256 56ad86f7973a67284731c7ff02e5b740a5e1738e95fe7f8bb2b72d736ac3d29d - references/5-post-design.md: SHA-256 ea90124e8c6caa5e9cdbd61480f4e94ac540c058e709dd1cac4b2c46a32f86df 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 6 files: SKILL.md plus 5 phase files under references/ (1-parse-arguments, 2-gather-context, 3-file-skeleton, 4-section-design, 5-post-design) that the SKILL.md reads and follows in turn — the real procedure lives mostly in those references, not in the SKILL.md alone. Nothing in the folder is a program; all six 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, system_overrides), reads the template's .claude/docs/ documents and its game-design-document template, spawns template specialist agents by system category, and in post-design runs the template's .claude/scripts/registry.sh to validate the entity registry — files 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 reads my project's concept or brief, systems index, GDDs and ADRs locally. - At use time it writes the GDD incrementally and only through approvals: the skeleton after an ask, then each section right after its own approval, the session state in production/session-state/active.md after each write, and — each after its own ask — the entity registry and the systems index. Specialist agents never write files; the main session owns all writes. No third-party service, account or credential is named in the files I read. - Do not design any system, 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 design-system folder into the agent's skills directory, in a folder named exactly "design-system", keeping its 6 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: design-system), the 6 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 — that it belongs to the full Claude Code Game Studios template and may not run standalone (its phases live in its references/ files and depend on the template's docs, templates, specialist agents and registry script), and that using it authors a GDD section by section in my project, each section written only after I approve it). 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.