Localize

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 "Localize" for me. It is the Game Studios localization pipeline, in ten subcommands. scan searches the code root read-only for hardcoded user-facing strings and localization anti-patterns. extract builds a diff of new string-table entries for assets/data/strings/strings-en.json and asks "May I write these new entries…?" before writing only the diff. validate and status are read-only (completeness, placeholder, length, plural-form and orphaned-key checks, and a coverage matrix that reports NOT ASSESSED when no string table exists). brief generates a translator context briefing meant to be sent by you to an external translation team or vendor with the string-table export, written to production/localization/translator-brief-[locale]-[date].md only after asking. cultural-review and qa spawn the template's localization-lead agent. vo-pipeline manages voice-over localization (recording scripts, manifests, file checks under assets/audio/vo/ and production/localization/). rtl-check validates right-to-left layout using engine.name from project.yaml. freeze locks the source string table by writing production/localization/freeze-status.md after a confirmation question, and can lift the freeze. With no subcommand it prints usage and stops with a FAIL verdict. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/localize/ 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/localize/ 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 321672db96810276c52b6630119d38bfeee8010cf6cd4a4f39511737ed450144 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 read or modified. - Integrated-system reality, from the file: at use time the skill resolves its automation mode by running the template's hooks/yaml-helper.sh, follows .claude/docs/automation-modes.md and .claude/docs/code-root-resolution.md, and reads my project's code root, assets/data/strings/, design/gdd/, design/narrative/, assets/ and project.yaml. Its cultural-review and qa modes spawn the template's localization-lead agent — files and an agent that live outside this skill's folder and are absent in a standalone install, so parts of it cannot run outside the full template. - At use time, scan, validate and status write nothing. Every writing mode asks first: the extract diff to assets/data/strings/, the translator brief, the cultural-review report (production/localization/cultural-review-[date].md), VO scripts, the RTL report, the QA report (production/localization/loc-qa-[locale]-[date].md) and the freeze file. The brief is a document for an external translation team, but sending it is my own step — the skill names no service, account or credential and sends nothing itself. - Do not run any localize mode, do not run any template hook 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 localize folder into the agent's skills directory, in a folder named exactly "localize", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: localize), 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 and its cultural-review and qa modes need the template's localization-lead agent), and that its scan, validate and status modes are read-only while every writing mode asks me first). 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.