Launch Checklist

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. It is user-invocable only (disable-model-invocation in its frontmatter), and its dry-run mode writes nothing at all. Install "Launch Checklist" for me. It builds a launch-readiness checklist across every department — code, content, QA, store and distribution, legal, infrastructure, community and marketing, operations — scoped to the project rather than emitted whole: items for unreached stages are out of scope, minimal-rigor process items are dropped, and the certification section is emitted only for the project's platform.cert_tier (none, itch, steam or console; an unset tier is a question to ask, never a licence to emit every track, and an undeterminable one marks the section NOT ASSESSED). It reads CLAUDE.md, the latest milestone, any existing release checklist and the content calendar, then scans the codebase for TODO, FIXME and HACK comments, debug output, placeholder assets and hardcoded test or dev values — every scan reporting its denominator (files scanned, hits found) or NOT ASSESSED when there was nothing to search, because a zero-hit scan on an empty root must not render as a green tick. It then asks, section by section, about the items only a person can confirm (on-call schedule, EULA, press keys, pricing, a soak test someone ran): unconfirmed items keep the overall status at NOT ASSESSED, and this questioning phase is skipped in autonomous mode and in dry-run, which also leaves the status NOT ASSESSED. The go/no-go decision follows a first-match rule — NOT READY if any blocking item stands, else NOT ASSESSED if anything is unchecked, else CONDITIONAL, else READY — with sign-offs required from the creative, technical, QA, producer and release-manager roles. Finally it presents the checklist and asks before writing it to production/releases/launch-checklist-[date].md, creating nothing before the answer, not even the directory; a dry-run run writes nothing at all. Its folder is a single SKILL.md. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/launch-checklist/ 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/launch-checklist/ 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 ce8813df00b1b1f513c935fa6fcefd560c293e96fee02040a7705063a6afa7d2 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 checklist instructions the session follows at use time. Its frontmatter sets disable-model-invocation: true — it runs only when the user invokes it. - 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 rigor, workflow, project.stage, cert_tier, automation), reads the template's .claude/docs/effects-map.md cert-tier section and its automation-modes document, and follows the template's production/ layout (milestones, releases, content calendar) — 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 and greps my project's own code and documents locally; its codebase scans look for TODO/FIXME/HACK comments, debug output, placeholder assets and hardcoded test or dev values, and report what they scanned. - At use time it writes exactly one file, and only after asking: production/releases/launch-checklist-[date].md — creating nothing before the answer, not even the production/releases/ directory. In dry-run mode (and for the human-confirmation phase in autonomous mode) it writes nothing and the unconfirmed items keep the verdict at NOT ASSESSED. It deploys nothing and contacts no store or service. No account or credential is named in the file I read; the hardcoded-value scan it performs looks for test credentials in my code as a launch risk, which is a search, not a collection. - Do not build any checklist, do not scan any project, 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 launch-checklist folder into the agent's skills directory, in a folder named exactly "launch-checklist", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: launch-checklist), 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 reads the template's effects-map and production layout), and that using it writes a single checklist file under production/releases/ only after I say yes, or nothing at all in dry-run mode). 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.