CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

setup-engine

Sets up and pins the engine version: web for a new project unless Godot, Unity or Unreal is named. Use to choose or upgrade it.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

78%Weight 40%Scale 1-5

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

A well-engineered router-style skill: the body stays lean, sequences 12 phases unambiguously, and delegates detail to a complete, verified set of one-level-deep reference files with explicit load-discipline rules. The only notable costs are a repeated compaction-recovery boilerplate line and validation loops that live in the referenced files rather than the overview.

DimensionReasoningScore

Conciseness

The body is a lean router: numbered phases each reduced to "Read `references/N.md` now and follow it", terse guardrails, and a tier-awareness block that conveys non-obvious project context. It falls short of anchor 5 because the recovery instruction "Read it again if the conversation was compacted or resumed during this phase" is repeated verbatim in ~11 sections when stating it once would suffice.

4 / 5

Actionability

Every phase gives an executable directive (read a specific named file and follow it), the entry hook is a concrete command, and Sections 9–10 include specific numbered instructions (e.g., "Read `docs/engine-reference/<engine>/VERSION.md`", "Update 'Last verified' dates"). Not anchor 5 because the body itself contains no code or commands for the core phases — those live in the referenced files, leaving minor gaps when read alone.

4 / 5

Workflow Clarity

The 12 sections form a coherent, explicitly ordered pipeline (parse → guided/lookup → config → docs → scaffold → verify → summarize) with subcommands (refresh, upgrade) routed to their own files, and Section 8 is a dedicated verification checkpoint. It sits below anchor 5 because validation details for the riskier phases (e.g., scaffolding, CLAUDE.md edits) are deferred to reference files rather than stated as explicit validate-and-retry loops here.

4 / 5

Progressive Disclosure

This is a model of one-level-deep disclosure: every phase points to a real, existing file in `references/` (all 13 cited files verified present), Appendix A is split out with explicit load discipline ("On any engine other than Godot, never load it"), and web is quarantined into `references/web.md` with exactly which sections it replaces. Clear overview, well-signaled references, easy navigation — a direct match for anchor 5.

5 / 5

Total

17

/

20

Passed

Description

75%Weight 40%Scale 1-5

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

A concise, third-person description that names concrete actions, concrete engine names, and a default behavior, with an explicit use clause. It is stronger than the midpoint on every dimension but stops short of comprehensive trigger coverage and fully explicit when-phrases.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Sets up and pins the engine version", "Use to choose or upgrade it" — plus a concrete default ("web for a new project unless Godot, Unity or Unreal is named"). It falls just short of anchor 5 because coverage has gaps: modes like refresh and the Godot/Unity/Unreal setup paths themselves are not described.

4 / 5

Completeness

Both parts are answered: the "what" is explicit ("Sets up and pins the engine version") and the "when" is present via "Use to choose or upgrade it" plus the engine-naming clause. It is not anchor 5 because the "when" is terse rather than a concrete trigger phrase like "Use when starting a game project or when the user names Godot, Unity, or Unreal".

4 / 5

Trigger Term Quality

Natural trigger terms are present: "Godot", "Unity", "Unreal", "engine", "version", "upgrade", "web" — phrases a user would plausibly say when needing this skill. Not anchor 5 because common variations like "game engine", "migrate", or "new project setup" are missing.

4 / 5

Distinctiveness Conflict Risk

The named engines (Godot, Unity, Unreal) and the engine-version-pinning focus give it a clear niche with minimal overlap risk against non-game skills. Minor overlap remains with generic web-project scaffolding skills via "web for a new project", keeping it below anchor 5.

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

Donchitos/Claude-Code-Game-Studios

Path

.claude/skills/setup-engine/SKILL.md

Reviewed

Table of Contents

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.