メニュー
Diagnose GameMaker gameplay, resource, build, and runtime failures from reproducible evidence. Use when the game behaves incorrectly, fails validation, or cannot build or run.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Create and modify GameMaker resources through structured project tooling. Use when working with objects, events, rooms, scripts, instances, project metadata, or resource relationships.
Use this skill to remove compatibility shims, legacy behavior wrappers, and import/export pass-through files by migrating call sites to direct ownership APIs.
Organize GameMaker resources, manage layout and naming, structure project notes, and establish reusable architectural systems. Use when organizing resources, naming systems, or structuring GameMaker projects.
Use Playwright to inspect, navigate, and play a running browser-based GameMaker game. Use when the user wants the agent to verify gameplay, menus, input, screenshots, browser behavior, or the exported HTML5 game loop. This skill is for operating the game through the browser like a player, not for editing code.
Understand and work with GameMaker Language (GML), including its syntax differences from JavaScript, GML-specific language constructs, data accessors, keywords, constants, and formatting conventions.
Apply adversarial verification during any meaningful code change before the approach hardens. Use for medium or larger changes where regressions, hidden coupling, ownership mistakes, or invalid assumptions are plausible. Skip only for trivial mechanical edits.
| name | gmloop-game-debugging |
| description | Diagnose GameMaker gameplay, resource, build, and runtime failures from reproducible evidence. Use when the game behaves incorrectly, fails validation, or cannot build or run. |
Start from evidence. Record the expected behavior, observed behavior, shortest reproduction, relevant room or resource, and whether the failure occurs during validation, build, startup, or play.
Use structured diagnostics, stack traces, resource inspection, deterministic state capture, and targeted tests before broad debug logging. When logging is necessary, log the smallest state transition or boundary that distinguishes working from failing behavior.
Fix the owning source rather than suppressing its downstream symptom. When the behavior is automatable, add or strengthen a regression test following the design guidelines in gmloop-gml-tests. Remove temporary instrumentation, rerun the minimal reproduction, then run the relevant resource validation, unit test, build, and runtime smoke checks (following AGENTS.md).
Report the root cause, evidence that confirmed it, changed resources or scripts, regression coverage, and any environment-dependent behavior not reproduced.
