Dev Story

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. Two behaviours specific to this skill are disclosed up front: at use time the programmer agents it briefs write real code and tests in my project, and two of its own writes — the session checkpoint and the evidence stamp — are made without an ask (see the introduction). It is also user-invocable only (disable-model-invocation in its frontmatter). Install "Dev Story" for me. It implements one story in code with tests, following its ADRs. It checks the story can start (governing ADR status and version against the story's stamp, control-manifest version, dependencies — reading references/version-mismatch.md only when a version actually differs), asks once before marking the story In Progress (its Status and Last Updated fields and its production/sprint-status.yaml entry), then briefs the right template programmer agent for the story's layer and type (engine-programmer, gameplay-programmer, ui-programmer, ai-programmer or network-programmer) plus the configured engine specialist, who checks the changed files afterwards and edits nothing. The programmer agents write the code and tests under the project's code and test roots; a Config/Data story needs no agent and its data file is edited directly after an ask. Two writes are exceptions to the ask-first pattern, stated in the SKILL.md itself: the session checkpoint (piped to the template's session-state.sh) and the evidence stamp are written without an ask. When the work is done it verifies the named files actually exist on disk, runs an engine parse check (for Godot, godot --headless import and parse-check runs — godot on PATH is pre-approved by this skill, while an engine run through engine.path or the commands.test executable asks first), and for any story a player can see it launches the game scene, captures a screenshot into production/qa/evidence/[story-slug]/ and reports exactly one Run result line (OBSERVED, NOT VERIFIED or N/A). It closes by replacing the story's Files section with the real changed-files list. Its folder also holds CONTRACT.md and two references (engine-checks for Unity/Unreal, version-mismatch). Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/dev-story/ folder at the pinned commit: 4 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/dev-story/ folder from that checkout. Then compare every file in the folder with the fingerprints recorded for this listing on 2026-10-22: [FINGERPRINTS] - CONTRACT.md: SHA-256 95abf80e16dfc28230989db818e6f8afeb05d73cb4600882855f598f5ee77071 - SKILL.md: SHA-256 ca76457c34ec9a8468c34bcc55664273eff2b077afbebe36f1dda0c8ec8e474d - references/engine-checks.md: SHA-256 c3ec789cc1c424366e5e85ebc56e5df317b5dfdd011f9e944e6242235640fdb4 - references/version-mismatch.md: SHA-256 2f38c7964569cba3b22bfbfc0cc702ecb1c4580e7aa294994b3047cae9318a41 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 4 files: SKILL.md, CONTRACT.md (the handoff contract for the story, ADR, manifest and session-state files) and references/engine-checks.md plus references/version-mismatch.md, each loaded only in its situation (Unity/Unreal parse checks; an ADR or manifest version mismatch). Nothing in the folder is a program; all four are instructions or contract text the skill reads at use time. Its frontmatter sets disable-model-invocation: true. - 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 automation, workflow, qa.level, gate_level, engine_values, specialists, perf_budgets, system_overrides) and calls template scripts under .claude/scripts/ (story-facts.sh, adr-status.sh, md-section.sh, session-state.sh, review-receipts.sh), spawns template programmer agents and the configured engine specialist, and runs the project's game engine for parse checks and screenshots — files, agents and tools that live outside this skill's folder and are absent in a standalone install, so it cannot run outside the full template. - At use time it produces real code: the programmer agents write code and tests under my project's code and test roots, the story is marked In Progress after one ask, and its Files section is replaced at the end. Two writes are exceptions, stated in the SKILL.md: the session checkpoint and the evidence stamp (a hash file under production/qa/evidence/[story-slug]/) are written without an ask. It also launches the game for player-visible stories and saves a screenshot there. No third-party service, account or credential is named in the files I read. - Do not implement any story, do not run any template hook, script, agent or engine, 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 dev-story folder into the agent's skills directory, in a folder named exactly "dev-story", keeping its 4 files in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: dev-story), the 4 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 — that it belongs to the full Claude Code Game Studios template and may not run standalone (it briefs the template's programmer agents, calls its .claude/scripts helpers and runs my game engine), and that using it writes real code and tests in my project, marks the story In Progress after one ask, and writes its session checkpoint and evidence stamp without an ask). 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.