axiom-games

Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit, or adding touch controls or game controller support. Covers scene graphs, ECS, physics, actions, game loops, rendering, TouchController, GCController.

Quality

100%

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

Quality

Content

100%

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

A well-architected router skill: lean, dense, and free of concept-overexplaining, with clear decision routing and one-level-deep references. The only caveat is that no bundle files exist in the reviewed directory, so the referenced skills/*.md targets could not be verified.

Suggestions

Verify the referenced bundle files (skills/spritekit.md, skills/game-input.md, skills/spritekit-diag.md, etc.) actually ship with the skill, since none are present in the reviewed directory.

Consider trimming the 'You MUST use this skill for ANY...' emphasis line — the description already establishes the trigger, so this adds tokens without guidance value.

Dimension	Reasoning	Score
Conciseness	Dense, token-efficient body using tables, a dot decision tree, and bulleted anti-patterns; assumes Claude's competence and avoids explaining concepts Claude already knows.	3 / 3
Actionability	Concrete symptom-to-reference routing, specific anti-patterns with real API names (0xFFFFFFFF bitmask, SKShapeNode draw calls, [weak self] in SKAction.run), and a scored auditor (PERFORMANT/DEGRADED/UNPLAYABLE) — appropriate executable guidance for a router skill.	3 / 3
Workflow Clarity	A graphviz decision tree plus a 15-step numbered routing list sequences multi-step decisions clearly, with diagnostic checklists (5-step bitmask checklist, tunneling flowchart) serving as validation checkpoints.	3 / 3
Progressive Disclosure	Overview body signals one-level-deep references (skills/*.md, axiom-graphics, axiom-integration, axiom-uikit) via a well-organized Quick Reference table; content appropriately split rather than inlined.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 tight, third-person description that names concrete capabilities and explicit use-when triggers with strong natural keywords. No fluff or over-claims; clearly scoped to a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists many concrete topics and actions — 'scene graphs, ECS, physics, actions, game loops, rendering, TouchController, GCController' — going well beyond naming a domain.	3 / 3
Completeness	Explicitly answers both what ('Covers scene graphs, ECS, physics...') and when ('Use when building ANY 2D or 3D game... or adding touch controls or game controller support').	3 / 3
Trigger Term Quality	Strong natural coverage users would actually say: 'game', 'SpriteKit', 'SceneKit', 'RealityKit', 'touch controls', 'game controller', plus API names.	3 / 3
Distinctiveness Conflict Risk	Narrow niche of Apple game frameworks with specific, non-overlapping triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: CharlesWiltgen/Axiom
Path: .claude-plugin/plugins/axiom/skills/axiom-games/SKILL.md
Commit: ea3be7c

Reviewed: 1 day 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.