CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

game-engine-development

Skill de implementacao real de codigo de engine de jogo — Unity C# e Unreal C++. Cobre padroes de MonoBehaviour, ScriptableObject, object pooling, state machine, ECS, componentes de Actor/UPROPERTY/ UFUNCTION do Unreal, otimizacao de performance (profiling, batching, LOD, culling, garbage collection), e networking multiplayer (cliente-servidor, predicao de cliente, lag compensation, serializacao). Cobertura conceitual de Godot GDScript quando pedido. Nao decide arquitetura de sistema nem balanceamento de numero — para isso ver skill 66. Trigger em: "Unity C#", "Unreal C++", "MonoBehaviour", "ScriptableObject", "UCLASS", "UPROPERTY", "UFUNCTION", "object pooling jogo", "ECS Unity", "otimizar FPS", "profiler Unity", "Unreal Insights", "multiplayer networking jogo", "client-side prediction", "lag compensation", "state machine jogo", "spatial partitioning", "coroutine Unity", "Blueprint callable", "smart pointer Unreal", "implementar sistema de jogo em Unity", "Godot GDScript".

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

The body is a well-structured router: dense hard rules, an accurate reference routing table, and a checkpointed workflow. Its weaknesses are mild redundancy — the Godot limitation is argued at length three times — and the absence of an error-recovery branch when a performance checkpoint fails.

Suggestions

State the Godot gap once, in 'Cobertura de Godot', and cut the intro and 'Fontes' restatements to one-line pointers — the full rationale currently appears three times in similar depth.

Trim the 'Fontes' curatorial meta-detail (e.g., the 'Nao portado' bullet enumerating the source repo's 66 unrelated skills) down to the attribution/license essentials needed for reuse.

Add an explicit recovery branch to the Fluxo de Trabalho checkpoints, e.g., 'se frame time > 16ms apos otimizacao, voltar ao passo 2 com o dado do profiler' — currently a failed checkpoint has no defined next action.

DimensionReasoningScore

Conciseness

The operational core is lean — the 'Regras Duras' do/don't table, the reference routing table, and checkpointed flux assume Claude's competence and explain nothing basic. However, the Godot gap rationale is stated in near-full depth three times ("Godot nao tem cobertura propria aqui" in the intro, the 'Cobertura de Godot' section, and the 'Gap reconhecido' bullet in Fontes), and 'Fontes' includes curatorial meta-commentary ("o repositorio tem 66 skills cobrindo dominios fora de jogo (React, Django, Kubernetes, etc.)") that is trimmable, matching anchor 4 rather than 5.

4 / 5

Actionability

Despite no inline code (by design, per the routing structure), guidance is copy-paste concrete: 'Cachear a referencia em Awake/BeginPlay', 'CompareTag() (Unity) ou enum/gameplay tag (Unreal)', 'UPROPERTY() pra referencia gerenciada, TWeakPtr pra evitar ciclo', with named tools and thresholds ('rodar Unity Profiler ou Unreal Insights, confirmar frame time ≤16ms'). The rules table covers exactly the common cases for this domain, matching anchor 5; per the rubric's scoring note, absence of code in a router-style skill is not penalized when guidance is this actionable.

5 / 5

Workflow Clarity

'Fluxo de Trabalho' gives a clear 5-step sequence with two explicit checkpoints ('confirmar frame time ≤16ms antes de prosseguir', 'rodar teste de latencia/dessincronia antes de liberar') plus a completion checklist in 'Evidencia de Conclusao'. It falls short of anchor 5 because there is no error-recovery feedback loop — nothing says what to do when a checkpoint fails (e.g., frame time exceeds 16ms), leaving a minor validation gap at anchor 4.

4 / 5

Progressive Disclosure

The routing table maps each topic to one of five one-level-deep reference files (all five verified present in references/), with an explicit just-in-time loading instruction ('carregar so o arquivo do motor/topico relevante a task, nao os cinco de cara') and a body that stays a genuine overview — a clear match to anchor 5's 'clear overview with well-signaled one-level-deep references'.

5 / 5

Total

18

/

20

Passed

Description

100%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.

The description is exemplary: a concrete what, an explicit 22-term trigger list, a stated non-scope with a handoff pointer, and honest limitation disclosure for Godot. It scores at the top of every dimension.

DimensionReasoningScore

Specificity

It opens with a concrete capability claim ('Skill de implementacao real de codigo de engine de jogo — Unity C# e Unreal C++') and enumerates multiple specific concrete capability areas — patterns ('MonoBehaviour, ScriptableObject, object pooling, state machine, ECS'), performance ('profiling, batching, LOD, culling, garbage collection'), networking ('cliente-servidor, predicao de cliente, lag compensation, serializacao') — with no vague language and comprehensive coverage of its declared scope, including the explicit Godot limitation. This matches anchor 5; it is above anchor 4 because coverage is comprehensive rather than gapped.

5 / 5

Completeness

It explicitly answers both questions: what ('Skill de implementacao real de codigo de engine de jogo — Unity C# e Unreal C++. Cobre padroes de...') and when ('Trigger em: "Unity C#", "Unreal C++", ...'), plus an explicit non-scope boundary ('Nao decide arquitetura de sistema nem balanceamento de numero — para isso ver skill 66'). This is a direct match to anchor 5's 'both what AND when with concrete trigger phrases'; the trigger clause is present, so the completeness-at-3 cap does not apply.

5 / 5

Trigger Term Quality

The explicit 'Trigger em:' list gives 22 natural phrases users would actually say, spanning engine-specific APIs ('UPROPERTY', 'MonoBehaviour', 'Blueprint callable'), PT-BR task phrasings ('otimizar FPS', 'implementar sistema de jogo em Unity'), and synonyms for the same need ('multiplayer networking jogo', 'client-side prediction', 'lag compensation'). This matches anchor 5's comprehensive natural-term coverage; not anchor 4 because synonym and task-level phrasings are present, not missing.

5 / 5

Distinctiveness Conflict Risk

The niche is clear and the triggers are engine-API-specific ('UCLASS', 'ScriptableObject', 'smart pointer Unreal'), which no adjacent skill would claim, and the explicit boundary ('Nao decide arquitetura... para isso ver skill 66') actively routes away from the nearest neighboring skill. Minimal conflict risk, matching anchor 5.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

felvieira/claude-skills-fv

Path

skills/67-game-engine-development/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.