CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

92%

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

85%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.

This is a high-quality, information-dense project skill: nearly every line records non-obvious project conventions, exact keys, and hard-won gotchas, with executable snippets and a validation workflow. Its main weakness is structure at scale — ~280 lines in a single file with no reference files, so distinct subsystems (audio, feature flags, cloud sync) are not progressively disclosed.

Suggestions

Split stable subsystem reference material (audio track/state-key inventory, Tinyverse feature flags, cloud sync endpoints) into references/ files linked one level deep from SKILL.md, keeping the overview, gotchas, and validation workflow inline.

Move time-sensitive values like 'currently 6 horizon + 1 rising' and legacy defaults ('1.1') into a clearly labeled migration/old-patterns section so they don't read as stable facts.

Trim narrative detail in the cloud-saves bullet list to the invariants (what must stay in sync) and push endpoint-specific behavior into a reference file.

DimensionReasoningScore

Conciseness

The body is dense and project-specific throughout (exact key names, exclusion regexes, gotchas) and assumes Claude's competence, but a few spots could be trimmed, and time-sensitive details like 'currently 6 horizon + 1 rising' and the old '1.1' default are not isolated in an old-patterns/deprecated section. Not 5 for those minor over-explanations; well above 3 since nothing explains concepts Claude already knows.

4 / 5

Actionability

Guidance is fully executable: copy-paste JS for relative panel positions and legacy-read compatibility, exact commands ('node tools/check.js', 'node tools/smoke-static.js'), exact keys, regexes, file paths, and function names covering the common cases. Not 4: there is no pseudocode and no missing key detail for the workflows it describes.

5 / 5

Workflow Clarity

The defaults pipeline is a numbered 5-step dev-to-users sequence, and the Validation section is an explicit 4-step checklist with commands and both clean-localStorage and existing-localStorage outcomes — a real feedback checkpoint for a write-and-ship operation. Not 4: validation steps are explicit rather than implicit, satisfying the destructive/batch cap concern.

5 / 5

Progressive Disclosure

The body has good section headers but is ~280 lines with everything inline and no bundle files; clearly separable material (audio system details, Tinyverse feature flags, cloud sync) sits in one file rather than one-level-deep references. Not 2 because structure is far from minimal and navigation via headers is easy; not 4 because content that should be split out is not, and the skill exceeds the simple-skill exception (under 50 lines).

3 / 5

Total

17

/

20

Passed

Description

95%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 description: it names a precise domain, enumerates concrete coverage areas, and opens with an explicit 'Use when' trigger clause with natural keywords. The only flaw is the informal first-person phrase 'has burned us twice', which breaks third-person voice and adds no trigger value.

Suggestions

Drop or rewrite the first-person aside 'that has burned us twice' (e.g., 'a recurring inline-script regex pitfall') to keep the description in third-person voice.

Consider naming the localStorage key prefix 'tinyworld:' as an explicit trigger term, since users may reference keys directly.

DimensionReasoningScore

Specificity

The description lists multiple concrete coverage areas ('settings defaults, audio, camera/orbit, panel positions, feature flags') plus a specific pipeline ('snapshots localStorage into tinyworld-defaults.json'), matching the comprehensive anchor. However, the first-person aside 'has burned us twice' violates the third-person voice guideline, reducing specificity by 1.

4 / 5

Completeness

It explicitly answers both: what it covers ('persisted user state — settings defaults, audio, camera/orbit, panel positions, feature flags, and the in-app "Save Defaults" pipeline') and when to use it ('Use when adding or changing persisted user state') with concrete trigger phrases. Not 4, because the 'when' clause is explicit and specific rather than merely present.

5 / 5

Trigger Term Quality

Natural trigger terms a user would actually say are comprehensively covered — 'settings defaults', 'audio', 'camera/orbit', 'panel positions', 'feature flags', 'Save Defaults', 'localStorage', 'tinyworld-defaults.json' — including synonyms and a concrete file name. Not below 5: no common variation for this domain is missing; not applicable above 5.

5 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (tinyworld persisted runtime state) anchored by project-specific artifacts ('tinyworld-defaults.json', 'Save Defaults pipeline'), so it is unlikely to trigger for the wrong skill. Not 4: no meaningful overlap with adjacent skills is left open.

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.

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

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.