Help

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 "Help" for me. It answers "what should I do next?" — a lightweight orientation, not a full audit. It is read-only: it reports findings and writes no files. It reads the template's workflow catalog (.claude/docs/workflow-catalog.yaml, outside this skill's folder) as the authoritative phase/step list, globs .claude/skills/*/SKILL.md to list installed skills the catalog does not cover, takes project.stage and workflow from the config resolved by the template's hooks/yaml-helper.sh, reads the STATUS and CHECKPOINT blocks of production/session-state/active.md, and checks step completion deterministically with the template's .claude/scripts/artifact-check.sh (one call per phase, or --path minimal on the minimal path, where a second template script, story-status.sh, prints the story list in route order). On the minimal workflow it follows the brief-based route (engine, game brief, stories, /dev-story, /story-done) and deliberately never presents the concept doc, GDDs, /create-epics, sprint plans or /gate-check as required; in production it reads production/sprint-status.yaml directly for per-story status. It presents one primary recommendation (done, next required step, optional steps, what comes after), asks about MANUAL steps instead of assuming, and never auto-runs the next skill — the user invokes it. Its allowed tools also include git log reads. Its folder is a single SKILL.md, running on the haiku model. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/help/ 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/help/ 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 3a5fd66a1e29fd86133ef3085e764cf0f8e15ce935ed06e9000580a577ddbeb6 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 orientation instructions the session follows at use time. Its model is haiku. - 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 project.stage, workflow), reads the template's .claude/docs/workflow-catalog.yaml, and runs template scripts under .claude/scripts/ (artifact-check.sh, story-status.sh) plus git log reads — files and scripts that live outside this skill's folder and are absent in a standalone install, so it cannot produce its orientation outside the full template. Inside the template it reads my project's session state and sprint status locally. - At use time it writes nothing at all: it is explicitly read-only, it never auto-runs the skill it recommends, and its one outward action is presenting the recommendation in the conversation. No third-party service, account or credential is named in the file I read. - Do not orient any project, do not run any template hook or 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 help folder into the agent's skills directory, in a folder named exactly "help", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: help), 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 reads the template's workflow catalog and runs its artifact-check and story-status scripts), and that it is read-only: using it only tells me the one next step in the conversation and never runs it for me). 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.