CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

89%

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

77%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.

An excellent router skill — unambiguous routing via symptom table, decision tree, and per-framework signposting, with genuinely valuable non-obvious content in the Anti-Rationalization and Critical Patterns sections. Its main weakness is redundancy: the routing map is restated five times across sections, inflating token cost by roughly a third.

Suggestions

Consolidate the routing map: keep the Quick Reference table and the numbered Decision Tree list, and cut the dot graph, the 'External Routes' prose (its rows duplicate the table), and most of the 'Example Invocations' section, which restates existing table mappings.

Remove or make concrete the orphan 'Cursor Subagent Routing' section — 'Delegate to the appropriate Cursor subagent when this router calls for a specialized auditor' names no specific agent or command and adds no actionable information beyond the later 'Automated Scanning' section.

Where the body cites local paths like `skills/spritekit.md` and `skills/game-input.md`, either ship those files in the skill bundle or state where they resolve, so the router's references are verifiable at load time.

DimensionReasoningScore

Conciseness

The same routing map is presented five times: the 24-row "Quick Reference" table, the "External Routes" prose bullets, the dot "Decision Tree" graph, the 15-item numbered decision list, and 14 "Example Invocations" — roughly a third of the file is duplication. The content itself is dense and non-obvious (not concept padding), keeping it above anchor 2, but it could clearly be tightened to one or two routing presentations.

3 / 5

Actionability

Routing guidance is highly specific and executable ("Physics bitmask issues (default 0xFFFFFFFF, missing contactTestBitMask...)" → `skills/spritekit-diag.md`; "Half-screen collider shapes for movement and camera (never small circles)"), and the instruction-only nature is fine for a router skill. Minor gaps: the orphan "Cursor Subagent Routing" section says to "Delegate to the appropriate Cursor subagent" with no concrete instruction, and the cited `skills/*.md` paths cannot be resolved within this bundle.

4 / 5

Workflow Clarity

This is a single-action router skill: route a symptom or task to one reference. That action is unambiguous — the decision tree, symptom table, and numbered list all map each input to exactly one target, and no destructive or batch operations exist that would require validation checkpoints.

5 / 5

Progressive Disclosure

The body is a model router: a concise overview with well-signaled, one-level-deep references ("See `skills/spritekit-diag.md`", "See axiom-graphics (skills/realitykit.md)") organized by symptom, framework, and task, matching the top anchor's structure. Note: no bundle files (references/, scripts/, assets/, skills/) were provided alongside SKILL.md, so the referenced paths could not be verified to exist in this bundle.

5 / 5

Total

17

/

20

Passed

Description

95%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 strong description with an explicit and concrete 'Use when' trigger clause and natural framework-level keywords that users would actually say. The only weakness is that the capability statement is a topic list ('Covers scene graphs, ECS, physics...') rather than action verbs, which slightly blurs what the skill does.

DimensionReasoningScore

Specificity

The description lists many concrete coverage areas ("scene graphs, ECS, physics, actions, game loops, rendering, TouchController, GCController"), but the verb "Covers" presents topics rather than actions performed, leaving what the skill does with them (build, diagnose, reference) implicit. This sits above anchor 3 (only 1-2 concrete actions) but below anchor 5 (comprehensive concrete actions).

4 / 5

Completeness

Both halves are explicit: "Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit, or adding touch controls or game controller support" answers when with concrete trigger phrases, and "Covers scene graphs, ECS, physics, actions, game loops, rendering..." answers what. The 'when' clause is fully explicit, so this exceeds anchor 4's 'when could be more explicit'.

5 / 5

Trigger Term Quality

Natural user phrasing is comprehensively covered: "building ANY 2D or 3D game", "SpriteKit, SceneKit, or RealityKit", "touch controls", "game controller support". These are exactly the terms a user would say when needing this skill; no common natural variant for the game-development niche is missing.

5 / 5

Distinctiveness Conflict Risk

SpriteKit, SceneKit, RealityKit, TouchController, and GCController are unambiguous Apple game-framework names forming a clear niche with distinct triggers. The emphatic "ANY 2D or 3D game" is bounded by the framework list, so conflict risk with non-game or non-Apple skills is minimal.

5 / 5

Total

19

/

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

CharlesWiltgen/Axiom

Path

axiom-cursor/skills/axiom-games/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.