Install
$ agentstack add skill-avelrl-skills-setup-engine ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Purpose: Choose a game engine or runtime direction and create the canonical project technical-preferences document.
Use when:
- a game project needs a runtime direction or a technical-preferences baseline
- the team needs one place for engine or runtime, target platforms, language, budgets, and tooling defaults
Do not use for:
- system decomposition
- writing individual system GDDs
- deep architecture ADR work
Inputs / Required Context:
- optional:
design/gdd/game-concept.md - required in guided mode: answers about 2D or 3D, target platforms, team experience, preferred language, licensing constraints
- optional explicit arguments: engine or runtime name plus version or language
Outputs / Owned Artifacts:
- owns
docs/technical-preferences.md - creates
docs/if it does not exist - uses
gamedev/templates/technical-preferences.md - marks decisions as provisional when concept or platform context is incomplete
Modes or Arguments:
- guided:
/setup-engine - runtime only:
/setup-engine web - runtime spec:
/setup-engine web typescript - engine spec:
/setup-engine unity 6 - engine spec:
/setup-engine unreal 5.6
Execution Rules:
- Read
design/gdd/game-concept.mdwhen it exists and extract project constraints, including any working or documentation language and player-facing language policy already fixed there. - In guided mode, ask only the minimum questions needed to narrow the engine or runtime choice.
- If the version is missing, verify the latest stable release before using it; if it cannot be verified, mark it unresolved instead of guessing.
- If the target runtime is browser-based, use
Game Studiowhen available as the runtime-specialist source for stack-specific guidance instead of copying Phaser, Three.js, or browser-UI doctrine into this skill. - If the target runtime is not browser-based, rely on official engine docs or project-local specialists for engine-specific implementation details instead of inventing a parallel doctrine here.
- Write or update
docs/technical-preferences.mdwith runtime or engine, target platforms, language, conventions, performance budgets, testing defaults, approved addons, and the current language policy. If the concept already fixed the language policy, carry it forward instead of inventing a new one. - End with the next handoff in the flow:
map-systems, thendesign-system, thenprototype.
Failure / Stop Conditions:
- stop if guided answers are too thin to narrow the runtime choice and return a short comparison instead of forcing a decision
- do not invent platform, budget, or addon decisions that the project has not made
Return Format:
- chosen or shortlisted runtime or engine
- provisional or confirmed status
- output path
- specialist source used, if any
- critical open decisions
- next recommended skill:
map-systems
Example Invocation:
/setup-engine web typescript/setup-engine unity 6/setup-engine unreal 5.6
Related Skills / Boundary:
- use
map-systemsafter engine setup to define the MVP design surface - use browser specialists such as
Game Studioonly for browser-runtime depth; keepdocs/technical-preferences.mdas the canonical artifact here - use
architecture-decisionlater for durable technical choices beyond engine selection
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: avelrl
- Source: avelrl/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.