Project Stage Detect

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 "Project Stage Detect" for me. It analyzes a project to detect its development stage (Concept, Systems Design, Technical Setup, Pre-Production, Production, Polish, Release) and its gaps — the "where are we?" diagnostic. It starts with a deterministic pass that runs the template script .claude/scripts/artifact-check.sh exactly as "bash .claude/scripts/artifact-check.sh", then scans design/, the code root, production/, prototypes/, docs/architecture/ and tests/. It always runs its detection heuristics and compares the observed stage against any stage configured in project.yaml (project.stage) or production/stage.txt, reporting disagreements explicitly instead of echoing the configuration. Which absences count as gaps depends on the resolved workflow tier: at minimal, missing GDDs, art bible, ADRs, epics and sprint plans are not gaps at all. It presents findings and asks before writing the report to production/project-stage-report.md. Note the tension the file itself carries: its frontmatter calls it a "Read-only diagnostic skill", yet its allowed tools include Write and its last step writes that report — after approval only. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/project-stage-detect/ 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/project-stage-detect/ 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 be78698fe68ddc7fa79a0d763a1f5e474b1b4c2947237c4ca741071ac1b8f4b8 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 — the artifact-check script it runs belongs to the template, outside this folder. - 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 scanned and no template script is run. - Integrated-system reality, from the file: at use time the skill resolves workflow and automation by running the template's hooks/yaml-helper.sh, runs the template's .claude/scripts/artifact-check.sh from the project root, and reads project.yaml, production/stage.txt, the report template at .claude/docs/templates/project-stage-report.md and the project's design, code, production, prototype, architecture and test folders — the hook, the script and the template 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 is presented as a read-only diagnostic, and its only write is the stage report at production/project-stage-report.md, only after it shows its findings and asks "May I write…?". It never silently writes files. No third-party service, account or credential is named in the file. - Do not detect any project stage, do not run the artifact-check script or 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 project-stage-detect folder into the agent's skills directory, in a folder named exactly "project-stage-detect", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: project-stage-detect), 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 runs the template's artifact-check.sh script and yaml-helper hook and reads the template's report template), and that despite its read-only-diagnostic label it writes its stage report after approval, as disclosed above). 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.