Day-One Patch
INTEGRATED SYSTEM: this skill belongs to the complete "Claude Code Game Studios" template (49 agents, 74 skills, templates and a studio CLAUDE.md); it assumes that template and its conventions.
- What
- INTEGRATED SYSTEM: this skill belongs to the complete "Claude Code Game Studios" template (49 agents, 74 skills, templates and a studio CLAUDE.md); it assumes that template and its conventions.
- Cost
- Free
- Needs
- 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.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — INTEGRATED SYSTEM: this skill belongs to the complete "Claude Code Game Studios" template (49 agents, 74 skills, templates and a studio CLAUDE.md); it assumes that template and its conventions. This listing installs only this skill's folder, without the rest of the system, and the skill may reference template agents or files that are absent outside the full template. It prepares a day-one patch after the gold master: a fix-only mini-sprint for safe P1/P2 bugs (nothing over 4 hours, no features, no refactoring). It verifies a passing release-gate record exists before trusting its lightweight QA, gets a rollback plan from the release-manager agent before any code is written, applies approved minimal fixes through the lead-programmer and qa-tester agents with targeted tests, and writes the patch record under production/releases/ after asking. User-invocable only. By @Donchitos, listed here with credit to its creator. MIT licensed. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into Muse📌 Pinned version: commit 05ad7c8Before 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. One wall specific to this skill: it is user-invocable only (disable-model-invocation in its frontmatter), and at use time it implements real code fixes through template agents and runs the project's test command — disclosed in the introduction below, never during installation. Install "Day-One Patch" for me. It prepares a day-one patch after the gold master is locked: a fix-only mini-sprint (no new features, no refactoring, no fix estimated over 4 hours), not a hotfix and not a full sprint. It first verifies its own premise — it reads project.stage (project.yaml, fallback production/stage.txt), the latest gate record in production/gate-checks/, the open bugs in production/qa/bugs/ and the latest security audit, and it stops or warns plainly when no passing release-gate record exists, because its lightweight QA pass is only justified by that gate. It classifies the open bugs for inclusion, presents the scope (included and deferred) for approval, and sums the effort against a one-day window. Before any code is written it spawns the template's release-manager agent for a rollback plan and asks before writing it to production/releases/rollback-plan-[version].md. For each approved code fix it spawns the template's lead-programmer agent to plan the minimal fix without writing, asks once for the whole set, then has the fixes implemented and verified by the template's qa-tester agent, running targeted tests with commands.test from project.yaml (recorded as NOT RUN when that setting is unset); config-only fixes are edited directly, after an ask naming the file and the exact value change. A qa-lead agent then decides between a targeted smoke check and a broader regression, and a NOT ASSESSED QA verdict is explicitly not a pass. Finally it asks before writing the patch record to production/releases/day-one-patch-[version].md. Its folder is a single SKILL.md. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/day-one-patch/ 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/day-one-patch/ 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 dcd3d710b55dfd9e426965850cb572945d00d5d2d52daf53e83682ad573da971 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 workflow instructions the session follows at use time. Its frontmatter sets disable-model-invocation: true — it runs only when the user invokes it. - 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: this skill runs no template hook — it reads project.yaml (stage, commands.test), production/stage.txt, gate records, bug files, sprint files and security audits directly — but it spawns template agents that live outside this skill's folder (release-manager for the rollback plan, lead-programmer for the fixes, qa-tester for verification, qa-lead for the QA gate) and calls other template skills (/smoke-check, /patch-notes, /bug-report, /retrospective), so it cannot run as designed outside the full template. - At use time it changes real code, but only through approvals: the rollback plan is written after an ask, code fixes are planned without writing, then applied only after one ask covering the whole set, targeted tests run with commands.test from project.yaml, and config-only fixes are edited directly only after an ask naming the file and the value change. The patch record is written after an ask. No third-party service, account or credential is named in the file I read. - Do not prepare any patch, do not spawn any template 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 day-one-patch folder into the agent's skills directory, in a folder named exactly "day-one-patch", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: day-one-patch), 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 spawns the template's release-manager, lead-programmer, qa-tester and qa-lead agents), and that using it prepares a day-one patch, applies approved code fixes and writes its rollback plan and patch record under production/releases/ only after asking). 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.