CtrlK
BlogDocsLog inGet started
Tessl Logo

author-game-levels

Author or revise readable, flat-world Three.js game levels. Use for movement and camera routes, collision and navigation, encounter zones, landmarks, objectives, pickups, motivated lighting, visibility, deterministic level data, or desktop and mobile playthrough verification.

74

Quality

91%

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

90%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.

A concise, highly actionable instruction skill with explicit validation checkpoints and clean section organization. The main gaps are an implicit rather than explicit inline retry loop and a monolithic single-file structure with no progressive references.

Suggestions

Add an explicit inline feedback loop for the validation/traversal phase (e.g., 'If a fixture or route fails: fix the level data, then re-run the fixtures before reporting') to lift workflow_clarity toward 5.

Consider extracting the source-to-light inventory field spec or the validation checklist into a references/ file referenced from the body, which would give the skill true one-level-deep progressive disclosure.

Optionally trim or consolidate the duplicated 'Do not...' lists in the gameplay-plane section to tighten conciseness further.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no preamble explaining Three.js, collision, or lighting concepts; every section delivers rules or checklists where each token earns its place.

5 / 5

Actionability

Provides highly concrete, specific guidance throughout (explicit "Do not add stairs, ramps..." prohibitions, a 6-step layout procedure, a named-field source-to-light inventory spec, and concrete validation assertions), which is fully actionable for an instruction-only skill where absence of code is not penalized.

5 / 5

Workflow Clarity

Presents a clear sequence (layout steps -> data/geometry validation -> browser traversal) with explicit validation checkpoints ("Assert", "Reject", "Check") and a reporting signal, but the inline fail->fix->re-validate feedback loop is implied across sections rather than spelled out as a tight loop.

4 / 5

Progressive Disclosure

No bundle files exist and the body is a single cohesive, well-organized file with clear section headers serving as navigation; it sits slightly above the under-50-lines exception and is monolithic, so it fits good-but-not-ideal structure with minor organization gaps rather than a fully split overview with one-level-deep references.

4 / 5

Total

18

/

20

Passed

Description

92%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, specific description that clearly states what the skill does and when to use it, with concrete capability domains and minimal conflict risk. Trigger-term coverage is good but slightly short of fully comprehensive synonyms.

DimensionReasoningScore

Specificity

Names the concrete action ("Author or revise readable, flat-world Three.js game levels") and enumerates many specific capability domains (movement/camera routes, collision/navigation, encounter zones, landmarks, objectives, pickups, motivated lighting, visibility, deterministic level data, desktop/mobile playthrough verification), giving comprehensive coverage with no notable gaps.

5 / 5

Completeness

Explicitly answers both "what" ("Author or revise readable, flat-world Three.js game levels") and "when" via the "Use for ..." clause listing concrete triggers, matching the anchor that requires both halves to be clearly and explicitly stated.

5 / 5

Trigger Term Quality

Includes natural trigger phrases a level author would say ("movement and camera routes", "collision and navigation", "encounter zones", "pickups", "playthrough verification") with good coverage, but the domain enumeration lacks some natural synonyms and there are no file-extension-style triggers, keeping it just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (flat-world Three.js game level authoring) with distinct, domain-specific triggers that are unlikely to fire for unrelated skills, giving minimal conflict risk.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
MengTo/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.