Code 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 "Code Review" for me. It is the Game Studios architectural code review. It is explicitly read-only: no files are written. It loads the target files and the project coding standards, identifies the engine specialists from project.yaml (treating a "null" specialist value as unset, never spawning it as an agent name), checks ADR compliance by finding ADR references in the story file, file headers or commit messages (git log) and bounded-reading only each ADR's Decision and Consequences sections, then works through standards compliance, architecture and SOLID checklists and game-specific concerns (delta time, allocations in hot paths, null handling, cleanup). Applicable engine specialists and, for Logic and Integration stories, the qa-tester are spawned in parallel via Agent; every specialist finding must be verified (file and line, quoted evidence, VERIFIED or UNVERIFIED confidence) before it enters the report. Its anti-fabrication block makes any section whose inputs are absent NOT ASSESSED — NO DATA, and the verdict ladder puts CHANGES REQUIRED first and never lets a review that skipped the engine check approve the code. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/code-review/ folder at the pinned commit: 1 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/code-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 3468d605b4627e0568c80d0732d1ab1281652641f3dede555191657c40571b8c 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 only: SKILL.md (13782 characters of instructions in a single file; there are no companion files in its folder). Nothing in the folder is run during installation; companion files are instructions/references the skill reads at use time, copied as-is. - 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 the automation mode by running the template's hooks/yaml-helper.sh, follows the template's .claude/docs/automation-modes.md and technical-preferences documents, reads the specialists block and engine name from project.yaml, runs git log for ADR references, and spawns the template's engine-specialist agents and qa-tester in parallel — agents and 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 own code, stories and ADRs locally. - This skill is read-only: it writes no file at use time, in my project or anywhere else; its output is the review report in conversation, ending with a question about how to proceed. No account, key, payment or third-party service is named in the files I read. - Do not review any code, do not spawn any specialist or template 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 code-review folder into the agent's skills directory, in a folder named exactly "code-review", keeping its 1 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: code-review), the 1 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 (its specialist reviews spawn template agents chosen from project.yaml), and that it is read-only: it reports on my code locally and writes nothing). 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.