Perf Profile

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 "Perf Profile" for me. It profiles a system, or the whole game with "full", against the project's committed performance budgets. It resolves the budgets by running the template's hooks/yaml-helper.sh (resolve_config for performance.enforce — warn, block or off — and get_effective_yaml_key for target framerate, frame budget, draw call limit and memory ceiling, falling back to design docs or CLAUDE.md). A metric with no committed budget is NOT ASSESSED, never a pass. The profiling itself is static codebase analysis — per-frame functions, loops, allocations, rendering and I/O hotspots — not a runtime profiler run; runtime profiling is left to confirm its candidates. It asks before writing the report to production/polish/[scope]-report-[date].md, and when a fix is rated medium or large effort it asks you to choose between implementing it, reducing scope, deferring to Polish, or escalating to the technical-director through other template skills. Repository: https://github.com/Donchitos/Claude-Code-Game-Studios (the skill is the whole .claude/skills/perf-profile/ 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/perf-profile/ 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 6d9d1967d68f06b2d3f4f4f8b144ea38894612d3cf9885e50c459fcfa8dc6e8b 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 read or modified and no budget is resolved. - Integrated-system reality, from the file: at use time the skill runs the template's hooks/yaml-helper.sh twice over (resolve_config and one get_effective_yaml_key call per budget key) to read the project's committed budgets from project.yaml / project.local.yaml, and analyzes my project's codebase locally — the hook and the project configuration live outside this skill's folder and are absent in a standalone install, so it cannot resolve budgets as designed on its own. - At use time it writes only after asking: its one persistent output is the report at production/polish/[scope]-report-[date].md, and NOT ASSESSED sections stay in the written file. It runs no profiler and no game build; its effort decisions route to other template skills (/scope-check, /architecture-decision, /sprint-plan) only when you choose them. No service, account or credential is named in the file. - Do not profile anything, do not run the yaml-helper 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 perf-profile folder into the agent's skills directory, in a folder named exactly "perf-profile", keeping its 1 file in their original relative layout (SKILL.md at its root). 4. Verify with no network calls: frontmatter valid (name: perf-profile), 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 (its budgets come from the template's yaml-helper hook reading project.yaml), that it is static analysis rather than a runtime profiler, and that it writes its report 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.