Design Review

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 Review" for me. It reviews one design document (a GDD) for completeness, internal consistency, implementability and design standards, before the document is handed to programmers. It opens with a freshness check: the template's .claude/scripts/review-receipts.sh compares the document, the entity registry and this skill's own file against the hashes stamped in the previous review log, and an unchanged document with a covering prior verdict is offered back instead of being re-reviewed at full price. It then reads the target document in full (in ranges, by heading), checks section presence deterministically with the template's gdd-structure-check.sh and applies the tier rules of the resolved workflow (8 sections required at full, 5 at standard plus Formulas when the system defines numeric rules, advisory at minimal), cross-checks every value the document states against design/registry/entities.yaml with a whole-document grep, validates the dependency graph, and tests each acceptance criterion for independent testability. In full review mode only, it spawns the template's specialist agents in parallel — adversarially briefed to find problems, never to validate — and a creative-director agent synthesises the final verdict (APPROVED, NEEDS REVISION, MAJOR REVISION NEEDED, or NOT ASSESSED when the review could not actually be performed). The review itself writes nothing: Phase 4 is explicitly read-only, and the only writes in the whole skill are optional and asked for one by one — updating design/gdd/systems-index.md, appending the review summary (with its receipt hash line) to the review log, or editing the GDD itself when the user picks "revise now". Its folder is a single SKILL.md. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/design-review/ 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/design-review/ 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 8ed70a1d109fdd5e1a765ae4b2198730c033fb183ac3e3539fa339c106cebe1f 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 a single file: SKILL.md. Nothing in the folder is a program; it is review instructions the session 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 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, system_overrides) and runs template scripts under .claude/scripts/ (review-receipts.sh check and hash, gdd-structure-check.sh) plus whole-document greps against design/registry/entities.yaml — files 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 GDDs, concept or brief, narrative files and CLAUDE.md locally. - The review itself is read-only: it writes nothing during its analysis and verdict phases. The only writes are optional follow-ups, each asked for separately: marking the system in design/gdd/systems-index.md, appending the review summary to design/gdd/reviews/[doc-name]-review-log.md, and — only if I choose "revise the GDD now" — editing the GDD to address blocking items. In full mode it also spawns template specialist agents and a creative-director agent, which write no files. No third-party service, account or credential is named in the file I read. - Do not review any document, do not run any template hook or script, 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-review folder into the agent's skills directory, in a folder named exactly "design-review", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: design-review), 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 — 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 and runs the template's review-receipts and gdd-structure-check scripts), and that the review itself is read-only, with any tracking update or GDD revision written only after I select 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.