tinyworld-runtime-state

Use when adding or changing persisted user state — settings defaults, audio, camera/orbit, panel positions, feature flags, and the in-app "Save Defaults" pipeline that snapshots localStorage into tinyworld-defaults.json. Also covers the inline-script regex gotcha that has burned us twice.

Quality

91%

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

Quality

Content

92%

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

An exceptionally actionable, concise body of project-internal operational knowledge with a strong validation workflow. The main gap is structural: a large multi-subsystem monolith with no reference files, where several subsystems could be split out for progressive disclosure.

Suggestions

Extract the larger, more self-contained subsystems (e.g. the Audio system and Feature flags sections) into reference files under ./references/ and link to them one level deep, leaving SKILL.md as a tighter overview.

Move the detailed cloud-sync / account-modal bullet list into its own reference doc, keeping only the invariant summary inline.

Add a short 'See also' navigation block near the top pointing to any extracted reference files so the overview reads as a hub.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence throughout — it never explains concepts Claude already knows and instead packs project-internal facts (localStorage keys, regex gotchas, file paths). Length reflects a genuinely large surface area rather than padding; nearly every line carries operational specifics.	3 / 3
Actionability	Provides executable code (setItem with topPct/leftPct, backward-compatible read-back, camera JSON shape), concrete regexes for the exclusion list, exact commands ('node tools/check.js', 'node tools/smoke-static.js'), and precise file paths — copy-paste ready guidance.	3 / 3
Workflow Clarity	The 'Defaults pipeline' is a numbered 5-step dev→all-users sequence, and the 'Validation' section is an explicit 4-step checklist with checkpoints (clean localStorage, confirm defaults seed, confirm user prefs are not overwritten), giving clear sequencing with verification for the risky persistence changes.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the ~280-line body covers nine distinct subsystems (audio, camera, feature flags, cloud saves, exports) as a single monolith with no bundle/reference files, so content that could be split out is inline. Not a 1 because navigation via headers is clean; not a 3 because nothing is offloaded to one-level-deep references.	2 / 3
	Total	11 / 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, specific, well-triggered description that names concrete capabilities and an explicit 'Use when' clause. Its only weakness is the colloquial first-person aside ('burned us twice'), which breaks the required third-person voice.

Suggestions

Rewrite 'the inline-script regex gotcha that has burned us twice' in third person, e.g. 'the inline-script regex gotcha that has caused repeated test failures'.

Consider adding a few broader natural-language trigger variants (e.g. 'persisting preferences', 'default settings') alongside the project-specific terms to widen recall.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions/capabilities ('settings defaults, audio, camera/orbit, panel positions, feature flags, and the in-app "Save Defaults" pipeline that snapshots localStorage into tinyworld-defaults.json'), which would normally anchor at 3, but the first-person phrase 'that has burned us twice' violates the third-person-voice guideline and reduces specificity by 1 per the rubric.	2 / 3
Completeness	Explicitly answers both: the trigger ('Use when adding or changing persisted user state') and the what (the enumerated state categories plus the Save Defaults pipeline and the inline-script regex gotcha).	3 / 3
Trigger Term Quality	Covers natural, varied terms a project developer would actually say — 'settings defaults', 'audio', 'camera/orbit', 'panel positions', 'feature flags', 'Save Defaults', 'localStorage' — giving good coverage rather than jargon-only language.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to this project's artifacts ('tinyworld-defaults.json', 'localStorage', 'Save Defaults pipeline', 'inline-script regex gotcha'), giving it a clear niche unlikely to fire for unrelated skills.	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-runtime-state/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.