Start

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. At use time it writes three project settings to project.yaml (and a legacy stage mirror file), only after an explicit yes — disclosed in full below. Install "Start" for me. The skill itself is the guided onboarding entry point for a first-time user of the studio template: it assumes no game idea, no engine and no experience. It first runs the template's .claude/scripts/project-state.sh and reads project.yaml (engine, concept or brief, design documents, code, and whether modes.rigor and modes.automation are already set), then asks where the user is starting from: A) no idea yet, B) a vague idea, C) a clear concept, or D) existing work; an answer that contradicts what it found on disk is challenged once, politely, before routing. It names the one immediate next step for the path (/brainstorm, /setup-engine or /project-stage-detect) but never runs that step itself, then shows a "What I'll set up" card with the inferred project stage and rigor, and asks "Save these to project.yaml (and the stage to production/stage.txt)?" Only on "Save them" does it write, through the template's set-stage.sh and config-set.sh helpers: project.stage (with its legacy mirror production/stage.txt), modes.rigor when not already set, and, after the Phase 5 automation question whose pick is itself the consent, modes.automation; any other answer writes nothing. It never writes modes.review_mode or production/review-mode.txt, nor any other knob the rigor fronts. It then lays out the full path for the chosen rigor and hands off with a single line, "Type [skill] to begin." If the project's origin_url still points at Donchitos' template repo, it warns that a push or pull request would go there and suggests renaming the remote, without running any git command. A returning user (engine and concept both present) is asked nothing and pointed to /help. Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/start/ 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/start/ 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 ab6e079a48c99479ac71deca11b9143a4b87874b6589e39c3e0a81422d9d1f32 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 audited, read or modified. - Integrated-system reality, from the file: at use time the skill runs the template scripts .claude/scripts/project-state.sh (read), and on approval set-stage.sh and config-set.sh (writes), reads project.yaml and the project's concept, design and code files, and follows .claude/docs/settings-guidance.md and automation-modes.md — scripts and docs that live outside this skill's folder and are absent in a standalone install, so it cannot run as designed on its own. - At use time it writes only the three settings named above (project.stage, modes.rigor, modes.automation in project.yaml, plus the stage mirror production/stage.txt), only after the explicit save answers described in this prompt; it never starts the next skill it recommends, and it runs no git command. No third-party service, account or credential is named in the file. - Do not onboard anyone, do not run project-state or any other template 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 start folder into the agent's skills directory, in a folder named exactly "start", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: start), 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 works through the template's .claude/scripts/ helpers and .claude/docs/ guidance), and that at use time it writes the stage, rigor and automation settings to project.yaml only after an explicit yes, and never runs the next step it recommends). 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.