tinyworld-lowpoly-world-prompt

Use when editing Tiny World Builder prompts, model-generated worlds, Auto suggestions, or any model behavior that should create coherent low-poly 3D board scenes.

Quality

65%

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 ./.codex/skills/tinyworld-lowpoly-world-prompt/SKILL.md

Quality

Content

61%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 strong, domain-specific instruction set with concrete field names, exact commands, and good section structure. Its main weaknesses are the absence of an explicit validation/verification loop for a batch generation process (capping workflow clarity) and a moderate amount of interleaved rationale that could be trimmed for token efficiency.

Suggestions

Add an explicit validation step for generated output (e.g. 'Verify emitted cells against the v4 schema before save; regenerate if validation fails') to establish a feedback loop and lift workflow clarity above the batch-operation cap of 3.

Trim justifying clauses that restate why a rule exists ('This preserves editable object structure...', 'so the stats describe the real rendered assets') to improve token efficiency.

Consider moving the long 'Offline random island generation' catalog/mapping detail into the referenced `docs/random-island-generation-assets.md` and keeping only the operative rules inline.

Dimension	Reasoning	Score
Conciseness	Most bullets are dense and load-bearing, but several over-explain context Claude can infer (e.g. 'This preserves editable object structure and avoids low-quality broad blocks', 'so the stats describe the real rendered assets'), and the random-island section runs long with rationale interleaved into instructions.	3 / 5
Actionability	Guidance is largely concrete and executable: specific field names (`terrainFloors`, `buildingType`, `customFootprint` ranges, `transform.rotationY`), exact npm commands, and concrete decompositions (skate park = ...); a few items state constraints without a runnable step.	4 / 5
Workflow Clarity	Sequencing for water bridges (put rivers down first, carve paths next, place bridge only when...) and the New world flow is explicit, but this batch/generation skill has no validation checkpoint or verify-fix-retry loop, and the rubric caps batch/destructive operations without validation at 3.	3 / 5
Progressive Disclosure	Content is well sectioned (Prompt principles, Primitive assembly, Voxel stamp, Auto suggestions, Offline random island generation) and points one level deep to an external manifest (`docs/random-island-generation-assets.md`); no bundle files are provided, and most content is appropriately inline with clear headers, though the random-island block could itself be split out.	4 / 5
	Total	14 / 20 Passed

Description

70%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 leads with a clear 'Use when' trigger tied to a specific product and behavior, giving it strong activation guidance and distinctiveness. It is let down mainly by specificity, where the actions are named at a domain level rather than as concrete enumerated operations.

Suggestions

List concrete actions in the description (e.g. 'tune Generate and Auto-suggestion prompts, enforce JSON schema output, guide customParts voxel stamps') to lift specificity toward 5.

Add a few natural synonyms users might say (e.g. 'Tiny World prompts', 'board scene generation', 'Auto suggestions') to broaden trigger coverage.

Tighten the 'what' half into an explicit capability list so the what/when split reads as two clear clauses.

Dimension	Reasoning	Score
Specificity	Names the domain (editing Tiny World Builder prompts) and a couple of concrete behaviors (model-generated worlds, Auto suggestions) but actions stay generic ('editing', 'create coherent low-poly 3D board scenes') without enumerating the specific operations the skill performs.	3 / 5
Completeness	It opens with an explicit 'Use when...' trigger clause giving the 'when', and the rest of the clause states the 'what' (model behavior creating coherent low-poly 3D board scenes); both are present, though the 'what' could be more concretely enumerated.	4 / 5
Trigger Term Quality	Covers natural user-facing terms like 'Tiny World Builder prompts', 'model-generated worlds', and 'Auto suggestions', plus the descriptive 'low-poly 3D board scenes'; a few common synonyms or extension-style phrasings are missing but coverage is solid.	4 / 5
Distinctiveness Conflict Risk	The trigger is anchored to a specific product (Tiny World Builder) and a narrow behavior (low-poly 3D board scene generation), making it largely distinct; only minor overlap risk with a generic '3D/world building' skill.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jasonkneen/tiny-world-builder
Path: .codex/skills/tinyworld-lowpoly-world-prompt/SKILL.md
Commit: 6a9a551

Reviewed: 3 days 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.