CtrlK
BlogDocsLog inGet started
Tessl Logo

tinyworld-island-and-planes

Use when changing the home island layout, edge dressing, undersides, autoincentive sponsor banner (now a top-left logo-adjacent DOM banner), plane/crop-duster flight paths, banner streamers, or which side of the island is "front".

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/tinyworld-island-and-planes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 dense, codebase-accurate reference packed with specific function/file/constant identifiers and concrete validation steps, scoring well on actionability and workflow clarity. It loses points on conciseness (discursive prose passages) and progressive disclosure (a 305-line monolith with no external reference files).

Suggestions

Tighten the materials/strata and rocket-plume prose paragraphs into bullet lists to cut tokens while preserving the project-specific identifiers.

Split the larger subsystem sections (Mooring 'Connect' cables, Plane/crop-duster system, Autoincentive banner) into one-level-deep reference files (e.g. references/mooring.md, references/planes.md) linked from SKILL.md so the top-level file stays a lean overview.

Add an explicit validate->fix->retry loop to the Validation section (e.g. 'If tools/check.js fails, fix and re-run until clean') to lift workflow clarity toward a 5.

DimensionReasoningScore

Conciseness

Almost every line is project-specific knowledge Claude lacks (function names, constants like EDITABLE_ISLAND_PROP_LOCAL_Z = -2.84, shader/material details), but the ~305-line body has discursive prose passages (materials/strata paragraphs, rocket-plume section) that could be tightened into bullets, placing it at 'mostly efficient but could be tightened'.

3 / 5

Actionability

Highly concrete with exact file names (23-particles-clouds.js, 18-scene-pick-xr.js), line numbers (~line 16340), named materials (M.boardSideEdge), CSS selectors, and the validation command 'node tools/check.js'; minor gaps only because most guidance is navigation/descriptive references rather than copy-paste runnable snippets.

4 / 5

Workflow Clarity

A dedicated Validation section with 'node tools/check.js' plus concrete visual checkpoints (default 8x8 then 20x20, planes behind island, audio pans L-R) and a sequenced buildHomeBorder() flow supply most checkpoints; not a 5 because it reads as a reference encyclopedia with a checklist rather than a full validate->fix->retry feedback loop.

4 / 5

Progressive Disclosure

Well-organized section headers structure a single ~305-line file with no bundle files (references/scripts/assets absent), but the 50-line simple-skill exception does not apply and several subsystems (Mooring interaction, Plane system, Autoincentive banner) could be split into one-level-deep reference files, leaving content that could be separate inline.

3 / 5

Total

14

/

20

Passed

Description

78%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 is specific, well-triggered, and highly distinctive to this island/planes codebase, with an explicit 'Use when' clause. It sits at 4 rather than 5 because its actions are bundled under a single verb ('changing') and the unifying capability is implied via enumeration rather than stated outright.

DimensionReasoningScore

Specificity

Quotes concrete change-targets ('home island layout, edge dressing, undersides, autoincentive sponsor banner... plane/crop-duster flight paths, banner streamers') naming several specific subsystems, though they share one verb ('changing') rather than distinct concrete actions, sitting just below the comprehensive-action anchor 5.

4 / 5

Completeness

Has an explicit 'Use when...' clause with concrete trigger scenarios ('changing the home island layout... or which side of the island is front'), but the 'what' is conveyed by enumerating change-targets rather than a clean capability statement, leaving it just short of anchor 5.

4 / 5

Trigger Term Quality

Good natural-term coverage including synonyms ('plane/crop-duster', 'banner streamers', 'sponsor banner') users would actually say; a 5 would require comprehensive synonyms/extensions, which this codebase skill has no file extensions to add.

4 / 5

Distinctiveness Conflict Risk

Highly codebase-specific triggers ('autoincentive sponsor banner', 'crop-duster', 'home island layout', 'front side') carve a clear niche with minimal overlap risk against any other skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
jasonkneen/tiny-world-builder
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.