Retrospective

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 "Retrospective" for me. The skill itself builds a sprint or milestone retrospective from the project's own records: the sprint or milestone plan, production/sprint-status.yaml when present, the sprint period's git log (it is allowed Bash git log), previous retrospectives and TODO/FIXME/HACK trends, producing completion metrics, a velocity trend, what went well and poorly, blockers, estimation accuracy, carryover and 3-5 action items. Inputs that are absent make their section NOT ASSESSED — NO DATA, and if every required input is absent it stops with that verdict instead of filling in a report. An existing retrospective triggers an AskUserQuestion (update it, or start fresh — archiving the old file by rename only inside the approved Phase 5 ask). It presents the retrospective and asks before writing it to production/retrospectives/retro-[name]-[date].md, and its closing question can optionally hand off to /sprint-plan new or /gate-check. It resolves the studio configuration (automation, workflow, qa.level) by running the template's hooks/yaml-helper.sh, outside this skill's folder. Its frontmatter pins model: sonnet. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/retrospective/ 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/retrospective/ 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 29b136a0f3ea57c09acbc6e97e18df413444305f26e2eeac35c7c99de9f9dc61 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. - 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 audited, read or modified. - Integrated-system reality, from the file: at use time the skill runs the template's hooks/yaml-helper.sh to resolve automation, workflow and qa.level, follows .claude/docs/automation-modes.md, runs git log locally for the sprint period, and reads my project's sprint and milestone files, sprint-status.yaml and previous retrospectives under production/ — files that 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 its persistent output is the retrospective file in production/retrospectives/, written only after its explicit ask; the optional archive rename of a previous retrospective happens only inside that same approved ask, never before. The git history it reads stays local. No third-party service, account or credential is named in the file. - Do not build any retrospective, do not run git log 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 retrospective folder into the agent's skills directory, in a folder named exactly "retrospective", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: retrospective), 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 resolves its settings through the template's yaml-helper hook and reads the template's production/ records and local git log), and that it writes its retrospective 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.