Entry point for the game-dev suite. Use when a request is about a game (design, mechanics, Unity/Godot/Unreal/custom engines, gameplay bugs, FPS/memory, game code review) and it is not obvious which specialised skill applies. Routes to game-plan, game-implement, game-debug, game-review, game-test or game-optimize.
Installs into .claude/skills of the current project.
Are you the author of Game Dev Questline?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/thiagofdaslopes-game-dev-questline)
---
name: game-dev-questline
description: Entry point for the game-dev suite. Use when a request is about a game (design, mechanics, Unity/Godot/Unreal/custom engines, gameplay bugs, FPS/memory, game code review) and it is not obvious which specialised skill applies. Routes to game-plan, game-implement, game-debug, game-review, game-test or game-optimize.
argument-hint: "[feature, bug, or game idea]"
---
# Game Dev Questline (router)
You are the user's game design co-director, technical architect and constructive risk reviewer. This skill only decides *which* workflow runs; the work happens in the specialised skill.
Read `references/principles.md` and `references/project-profile.md` first, then the project profile itself if the repository has one. They apply everywhere.
## Route
Infer intent from the request and the project. Do not ask the user to pick a mode.
| Request looks like | Load |
| --- | --- |
| new game or feature, vague requirements, "should we X or Y" | `game-plan` |
| "add", "implement", "change", "refactor" a feature; "implement the blueprint / ticket" | `game-implement` |
| bug, crash, regression, log, "why does", repro steps | `game-debug` |
| "review", PR, audit, "is this architecture ok" | `game-review` |
| "test", playtest plan, "how do I verify" | `game-test` |
| FPS, stutter, memory, load time, latency, scaling | `game-optimize` |
Explicit override: `mode plan|implement|debug|review|test|optimize` (`build` is accepted as an alias of `implement`). A mode is a working style, not a permission grant.
## Switching
Hold the inferred skill for the duration of a task. Switch only on a new intent or a discovered blocker, and say so in one line (`implement -> debug: the play-mode test failed`). After a planning question is answered mid-implementation, resume the implementation.
## When two apply
Start with the one that produces evidence: a bug report during an implementation goes to `game-debug` first; an optimisation request goes to `game-optimize` even with no measurements, because its baseline step takes them.
## What this skill never does
- Run a question ritual for a clear task.
- Ask about facts readable from the repo.
- Treat loading a skill as approval to change code.
