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

77%

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

65%

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

The content is exceptionally concrete and actionable but over-long and monolithic, with the random-island generation spec living inline rather than in a reference file and lacking explicit validation feedback loops.

Suggestions

Move the detailed offline random-island generation spec (lines ~88-179) into a references/ file (e.g. references/random-island-generation.md) and keep only the entry-point summary plus a clearly signaled link in SKILL.md.

Tighten the prompt-principles and voxel-stamp sections by collapsing near-duplicate rules (e.g. material-name guidance appears in multiple forms) to reduce token load.

Add an explicit validate->fix->retry checkpoint sequence for the batch world-generation workflow so each generation pass is verified before save output.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basics Claude already knows, but at ~175 lines it is dense and padded — particularly the ~90-line offline random-island spec — and could be tightened or offloaded to a reference.	2 / 3
Actionability	Guidance is highly concrete for an instruction-only skill: exact JSON fields (gridSize, terrainFloors, customParts, kind), explicit token->kind mappings, a numeric count profile, and runnable npm commands.	3 / 3
Workflow Clarity	Sequencing appears in places (rivers -> paths -> water-bridge) and validation is mentioned ('final validation repairs any displaced floors'), but there is no structured validate->fix->retry feedback loop for this batch generator, capping it at 2.	2 / 3
Progressive Disclosure	Sections are clearly headed, but the file is monolithic with no bundle files present; the long random-island spec is inline material that belongs in a separate reference, and the one cited doc is a repo path rather than a local bundle reference.	2 / 3
	Total	9 / 12 Passed

Description

90%

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, niche-specific description with an explicit 'Use when' trigger and good natural keywords; its only weakness is that the action verbs are narrow ('editing', 'create') rather than a list of distinct concrete capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain and several targets ('Tiny World Builder prompts, model-generated worlds, Auto suggestions') but the verbs are limited to 'editing' and 'create', not the multiple distinct concrete actions the top anchor requires.	2 / 3
Completeness	An explicit 'Use when editing...' clause gives the trigger, and 'should create coherent low-poly 3D board scenes' states the behavior, answering both what and when.	3 / 3
Trigger Term Quality	Terms like 'Tiny World Builder', 'Auto suggestions', and 'low-poly 3D board scenes' are exactly what a user of this niche would naturally say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to Tiny World Builder / low-poly board scenes, with distinct triggers unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 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: f21f84b

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.