setup-engine

Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/setup-engine/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clear, well-validated multi-step workflows, but it is monolithic and over-long: large reference-style tables and a sizeable appendix are inline rather than split into separate files, and some guardrails are repeated.

Suggestions

Split the per-engine specialist routing tables and Appendix A into separate reference files under references/ and link to them from the body, reducing the SKILL.md footprint.

De-duplicate the GDExtension guardrail so the rule appears once (e.g. in Appendix A1) rather than repeated in the Guardrails section.

Tighten Section 2's recommendation prose; the honest tradeoffs are valuable but the surrounding narration can be condensed.

Dimension	Reasoning	Score
Conciseness	Mostly dense, domain-specific guidance Claude does not reliably know (engine tradeoffs, naming conventions, routing tables), but at 717 lines it carries repetition — e.g. the "C++ via GDExtension" guardrail restated at lines 580 and 600 — and Section 2's prose could be trimmed.	2 / 3
Actionability	Provides copy-paste markdown templates, exact WebSearch query strings, AskUserQuestion prompts with enumerated options, directory layouts, and file-extension routing tables — fully executable and specific.	3 / 3
Workflow Clarity	Twelve numbered sections with explicit sequencing and pervasive validation checkpoints ("Wait for confirmation before..." in Sections 4, 5, 7, 8, 9, 11), including an audit-then-confirm feedback loop in the upgrade subcommand.	3 / 3
Progressive Disclosure	No bundle files exist and everything — including the large Appendix A and the per-engine Unity/Unreal specialist routing tables — is inline in one 700+ line monolith; the reference-style tables could be split into separate files for easier navigation.	2 / 3
	Total	10 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinct, naming concrete actions and a clear niche, but lacks an explicit "Use when..." trigger and surfaces few natural user phrasings, capping completeness and trigger-term quality.

Suggestions

Add an explicit "Use when..." clause naming the natural triggers, e.g. "Use when starting a game project, choosing between Godot/Unity/Unreal, or pinning an engine version in CLAUDE.md."

Surface the natural engine names (Godot, Unity, Unreal) and common phrasings like "set up engine" or "pick a game engine" as trigger terms.

Lead with the user-facing outcome (engine selection and project configuration) before the internal mechanics (CLAUDE.md pinning, knowledge-gap detection).

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Configure the project's game engine and version", "Pins the engine in CLAUDE.md", "populates engine reference docs via WebSearch" — rather than vague language.	3 / 3
Completeness	Clearly answers what the skill does, but "when" is only implied ("when the version is beyond the LLM's training data"); there is no explicit "Use when..." trigger clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	Engine and version keywords are present but natural user phrasings ("set up my engine", "configure Godot/Unity") are not surfaced; framing leans on internal mechanics like CLAUDE.md pinning.	2 / 3
Distinctiveness Conflict Risk	The game-engine configuration niche with CLAUDE.md/reference-doc mechanics is clearly distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (717 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/setup-engine/SKILL.md
Commit: 984023d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.