unreal-mcp

Automate Unreal Engine editor scenes, actors, and renders.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/unreal-mcp/SKILL.md

Quality

Content

85%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, highly actionable overview that assumes Claude's competence and pushes detail into five clearly signaled, real reference files. Its workflows include explicit validation, feedback loops, and a checklist; the only weaknesses are minor verbosity in the summary pitfalls and the fact that complete call sequences live in recipes.md rather than inline.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — e.g. "Units are centimeters; axes are Z-up, X-forward", "hermes mcp install unreal-engine", "Default bind is http://127.0.0.1:8000/mcp" — with no padding about concepts Claude already knows. It is not a 5 because the "top of mind" pitfalls section partially duplicates references/pitfalls.md and passages like the licensing note could be trimmed.	4 / 5
Actionability	Concrete, executable guidance throughout: exact commands ("ModelContextProtocol.StartServer", "ModelContextProtocol.RefreshTools"), config paths ("~/.hermes/config.yaml" under "mcp_servers.unreal-engine"), and qualified toolset names. It is not a 5 because the full copy-paste call sequences for common builds are deferred to references/recipes.md rather than appearing inline in the body.	4 / 5
Workflow Clarity	The seven-step Operating Loop is clearly sequenced with explicit validation checkpoints ("Inspect first", "Read every result", "Verify visually and structurally", "Save often"), feedback loops (read values back, fix before moving on), and a closing Verification Checklist. Destructive/non-undoable editor edits are explicitly guarded, so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with a Reference Files table signaling five one-level-deep files (tool-surface.md, advanced-workflows.md, scene-craft.md, recipes.md, pitfalls.md), all of which exist in ./references/. Content is appropriately split — overview and rules inline, catalogs/recipes/cheat-sheets in references — with easy navigation and no nested references.	5 / 5
	Total	18 / 20 Passed

Description

57%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 concise, distinct, and names concrete targets, but it is held back by a missing "Use when..." trigger clause and limited keyword coverage (no UE5/level/lighting/cinematics synonyms). It reads as a tight what-only statement rather than a complete what-and-when description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to build or dress levels, spawn/move/delete actors, set up lighting, frame camera shots, or capture screenshots/renders in Unreal Engine 5."

Include common synonyms and the short form users say — "UE5", "Unreal", "levels", "lighting", "cinematics" — to improve trigger-term coverage.

Expand the single verb "Automate" into a few distinct concrete actions (build levels, spawn actors, set up lighting, render) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Quotes "Automate Unreal Engine editor scenes, actors, and renders" — it names the domain plus three concrete targets (scenes, actors, renders) but uses a single verb ("automate"), so coverage is not comprehensive. It is above the score-2 anchor (which only names the domain) but lacks the several distinct verbs of the score-4 anchor.	3 / 5
Completeness	It gives a clear "what" (automate scenes, actors, renders) but contains no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	The terms "Unreal Engine", "scenes", "actors", and "renders" are natural user phrases, but common variations/synonyms a user would say — UE5, level, lighting, cinematics, blueprints — are absent. This matches "some relevant keywords but missing common variations or synonyms" better than the score-4 anchor, whose missing set is only "a few".	3 / 5
Distinctiveness Conflict Risk	"Unreal Engine editor scenes, actors, and renders" carves out a clear niche (Epic's editor-embedded MCP automation) with distinct triggers and minimal overlap risk with other skills. It is not a 4 because no closely related skill shares these specific editor-automation triggers.	5 / 5
	Total	14 / 20 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/unreal-mcp/SKILL.md
Commit: 6680afb

Reviewed: about 4 hours 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.