Prototype

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 "Prototype" for me. Unlike most Game Studios skills, this one builds something: a fast, throwaway concept prototype that answers one falsifiable question — "is this core idea actually fun to interact with?" — normally right after /brainstorm and /setup-engine, before any GDD is written. The SKILL.md is a router: each of its nine phases, plus spike mode, lives in its own file under references/ that it reads and follows in turn. It defines the hypothesis with you, loads the concept context, picks a path (HTML: a single self-contained prototype.html; Engine: throwaway code in the project's engine; Paper: rules.md plus a simulated play-log.md), plans, then — after asking "May I create the prototype directory…?" — writes the prototype code into prototypes/[concept-name]-concept/, every file headered "PROTOTYPE - NOT FOR PRODUCTION". After a playtest debrief it writes REPORT.md and a prototypes/index.md row (asking first), records a session checkpoint in production/session-state/active.md (asking first), and ends in a PROCEED, PIVOT, KILL or NOT ASSESSED verdict; a creative-director review (gate CD-PLAYTEST, in references/8-cd-review.md) runs in full review mode. Spike mode (--spike) is a ~4-hour mid-production variant writing prototypes/[name]-spike-[date]/SPIKE-NOTE.md. Prototype code must never import production code, nor production import it, and a PROCEED means the production version is written from scratch. The references also suggest, as your own optional step, distributing an HTML build through itch.io or community channels for outside feedback — the skill itself uploads nothing. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/prototype/ folder at the pinned commit: 11 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/prototype/ 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 3fc9e89b027234972d595df6adf2d6b6ed501aae7bd11a24fe3887d0e92f0956 - references/1-question.md: SHA-256 0e3e23eb0e55f565292ee744ccd102d1297c8b95e82ab891624b9634ffb68954 - references/2-load-context.md: SHA-256 be6b3a58b15b69a7d4dd1bf6f54daf70c0abfb05016c8f5f2fe91d40154330ef - references/3-choose-path.md: SHA-256 66e109f694bea94d07b9ba4d33fa577028cb8c0fb23f1e1fc4f6d8bac9a227d8 - references/4-plan.md: SHA-256 8e2c9901b370d38506cfc9253d6035de4f5796e91da2088b1511f51f5b9e0072 - references/5-implement.md: SHA-256 49ed558badc1b7f5c539094fdaf61f3fa1197ed65f072916bef35b3fd1130c78 - references/6-debrief.md: SHA-256 cc1f527562b4c202ae09050738c041950d0bbf78b08370c422bcafd08fec8b76 - references/7-report.md: SHA-256 d04c5a675e652a83aa5f7bdfa166004324874a667ae5891100a97250f604c8ab - references/8-cd-review.md: SHA-256 cb05e4a4667666af6517ec469b3b3094ad1ac6bacd2b69c04b28ae126b2e1f03 - references/9-summary.md: SHA-256 9773ac9f283228d16dc7bcb23217f6da2b43f58aa19a34cc7b2127dbdf327ba1 - references/spike-mode.md: SHA-256 52588d00b47dca01513730126e70dab8af627c9e23eb5a8f6491f9cb586aaffe 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 11 files: SKILL.md plus 10 phase files under references/ (1-question, 2-load-context, 3-choose-path, 4-plan, 5-implement, 6-debrief, 7-report, 8-cd-review, 9-summary, spike-mode) that the SKILL.md reads and follows phase by phase. Nothing in the folder is a program; the reference files are instructions read at use time — but following them writes new prototype code in my project, as the next points state. - 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 prototype is built and no project file is written. - 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), reads the concept from design/gdd/game-concept.md or design/game-brief.md and the engine from project.yaml, reads the template's prototype-report template under .claude/docs/templates/, and in full review mode spawns the template's creative-director 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 it is a builder, and every creation is asked first: the prototype directory prototypes/[concept-name]-concept/ and its code (a single prototype.html, engine files, or paper rules.md + play-log.md, all headered PROTOTYPE - NOT FOR PRODUCTION), the session checkpoint production/session-state/active.md, REPORT.md plus the prototypes/index.md row, PIVOT-NOTE.md on a pivot and a prototypes/GRAVEYARD.md entry on a kill, and in spike mode the spike folder, its SPIKE-NOTE.md and clearing the session state. It never imports production code and production never imports it. No account, key or payment is named; the itch.io or community distribution mentioned in the references is a suggestion for me, not something the skill does. - Do not build any prototype, 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 prototype folder into the agent's skills directory, in a folder named exactly "prototype", keeping its 11 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: prototype), the 11 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 (it resolves its settings through the template's yaml-helper hook and reads the template's report template and, in full mode, its creative-director agent), and that at use time it writes throwaway prototype code and reports in my project, each creation asked first, and never touches production code). 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.