CtrlK
BlogDocsLog inGet started
Tessl Logo

unreal-engine-cpp-pro

Expert guide for Unreal Engine 5.x C++ development, covering UObject hygiene, performance patterns, and best practices.

44

Quality

46%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/unreal-engine-cpp-pro/SKILL.md

The canonical home for this skill is unreal-engine-cpp-pro in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Scale 1-5

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

This is a competent UE5 C++ skill with good executable code examples and a useful PR checklist, but it suffers from moderate verbosity—particularly the 'When to Use' section and naming conventions that Claude likely already knows. The skill covers broad territory without leveraging progressive disclosure or providing explicit validation workflows for the destructive/complex operations it touches on (memory management, GC).

Suggestions

Remove or drastically condense the 'When to Use' / 'Do not use' section and the naming conventions table, as these are well-known to Claude and consume significant tokens.

Add an explicit debugging/validation workflow for GC issues (e.g., steps to identify dangling UObject pointers, verify UPROPERTY coverage, use Unreal's memory profiling tools) with feedback loops.

Split detailed content (e.g., async loading patterns, debugging techniques) into separate referenced files to improve progressive disclosure for this broad-scope skill.

Add a concrete code example for delegate cleanup in EndPlay, since it's referenced in the checklist but has no accompanying implementation.

DimensionReasoningScore

Conciseness

The 'When to Use' / 'Do not use' section is verbose and explains things Claude would already know (e.g., 'Working on non-Unreal game engines'). The 'Core Principles' section has some unnecessary explanation (e.g., explaining what IsValid does). The naming conventions section lists well-known UE conventions Claude likely already knows. However, the code examples and patterns sections are reasonably tight.

3 / 5

Actionability

The skill provides concrete, executable C++ code examples for component lookup, interface implementation, async loading, and debugging. The checklist is actionable. Minor gaps exist—e.g., the async loading example mentions StreamableManager but doesn't show how to use it, and the delegate cleanup mentioned in the checklist has no code example.

4 / 5

Workflow Clarity

The PR checklist provides a useful validation step, and the patterns are sequenced (e.g., cache in BeginPlay, use in Tick). However, there's no explicit multi-step workflow with validation checkpoints or feedback loops. For a skill covering UObject hygiene and memory management, the absence of a debugging/validation workflow (e.g., how to detect GC issues, verify UPROPERTY coverage) is a gap.

3 / 5

Progressive Disclosure

The content is reasonably structured with clear section headers, but everything is inlined in a single file with no references to supporting documents. The naming conventions table and the 'When to Use' section could be separated or condensed. For a skill of this breadth (GC, reflection, performance, debugging, conventions), some content would benefit from being split into referenced files.

3 / 5

Total

13

/

20

Passed

Description

36%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 identifies its domain (Unreal Engine 5.x C++) but relies on abstract category labels rather than concrete actions, and completely lacks a 'when to use' clause. It reads more like a topic heading than a functional skill description, making it difficult for Claude to confidently select this skill from a large pool.

Suggestions

Add a 'Use when...' clause with explicit trigger phrases, e.g., 'Use when the user asks about Unreal Engine C++ code, UObject lifecycle, garbage collection, UPROPERTY/UFUNCTION macros, or UE5 performance optimization.'

Replace abstract labels like 'best practices' and 'performance patterns' with concrete actions, e.g., 'Reviews UObject memory management, implements delegate patterns, diagnoses GC issues, generates UPROPERTY/UFUNCTION boilerplate.'

Include common synonyms and abbreviations users would naturally say, such as 'UE5,' 'Blueprints,' 'Actor,' 'Component,' 'garbage collection,' '.cpp,' '.h'.

DimensionReasoningScore

Specificity

Names the domain (Unreal Engine 5.x C++ development) and mentions broad topic areas like 'UObject hygiene, performance patterns, and best practices,' but these are category labels rather than concrete actions. No specific actions like 'generates boilerplate,' 'reviews memory management,' or 'implements delegates' are listed.

2 / 5

Completeness

Provides a vague 'what' (expert guide covering certain topics) but completely lacks a 'when' clause. There is no explicit trigger guidance for when Claude should select this skill, which per the rubric should cap completeness at 3, and the weak 'what' brings it to 2.

2 / 5

Trigger Term Quality

Includes relevant keywords like 'Unreal Engine 5.x,' 'C++,' 'UObject,' and 'performance patterns' that users might mention. However, it misses common natural terms like 'UE5,' 'Blueprints,' 'garbage collection,' 'UPROPERTY,' 'UFUNCTION,' 'Actor,' 'Component,' or file extensions like '.cpp'/'.h'.

3 / 5

Distinctiveness Conflict Risk

The mention of 'Unreal Engine 5.x' and 'UObject' provides some specificity, but 'C++ development' and 'best practices' are broad enough to overlap with general C++ coding skills or other game engine skills. The lack of concrete actions increases ambiguity.

3 / 5

Total

10

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.