CtrlK
BlogDocsLog inGet started
Tessl Logo

tinyworld-single-file

Use when editing the Tiny World Builder repo, especially tiny-world-builder.html, to preserve the static classic-script Three.js r185 app structure and local edit/reload workflow.

65

Quality

77%

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-single-file/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 SKILL.md body is an excellent repo-specific rulebook: executable commands, the exact validation regex that has caused real failures, and a clear edit→build→validate workflow with explicit checkpoints. Its only gaps are a few verbose clauses and a couple of subsystems (random-island-preview, Cluso embed) that read as inlined reference material.

Suggestions

Split the random-island-preview and Cluso embed paragraphs into a short 'Subsystems' section or a referenced file to keep Core rules scannable.

Trim the parenthetical asides ('Owner-approved override of the prior rule') into a one-line note so the core rule reads cleanly.

Consider a one-line 'Quick reference' summary of the pinned version (Three.js r185) and build commands at the top for fast lookup.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific rules and gotchas Claude would not know (Cluso embed exclusion, the check.js regex conflation, vendor bundle regeneration) and avoids explaining general concepts; a few clauses are slightly verbose (e.g. the long random-island-preview sentence, 'Owner-approved override of the prior rule' aside), so it sits at anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed').

4 / 5

Actionability

It gives concrete, executable commands and code throughout — 'npm run vendor:three', 'npm run build', the perl/node parser one-liner, 'http://localhost:3000/tiny-world-builder', the exact check.js regex, and copy-paste HTML examples — fully executable and covering the common cases, matching anchor 5 ('Fully executable; copy-paste ready code or commands; specific examples cover the common cases').

5 / 5

Workflow Clarity

The body sequences edit-time rules, an explicit validation block (npm test, parser one-liner, browser check, console errors), and a feedback-loop gotcha ('has burned us twice') with regex + fix pattern; validation checkpoints and error-recovery guidance are explicit, fitting anchor 5 ('Clear sequence with explicit validation steps; feedback loops for error recovery').

5 / 5

Progressive Disclosure

Content is well-organized into labeled sections (Core rules, Validation, the script gotcha, Related durable systems) with one-level-deep pointers to sibling skills (.codex/skills/tinyworld-runtime-state, tinyworld-island-and-planes); however no bundle files exist and some durable detail (random-island-preview, Cluso) is inlined rather than split out, so it lands at anchor 4 ('Good structure; most content appropriately placed; minor organization gaps').

4 / 5

Total

18

/

20

Passed

Description

66%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 highly distinct and tightly scoped to a specific repo and file, with an explicit 'Use when' trigger covering both what and when. Its weaknesses are mild verbosity in the 'what' clause and limited enumeration of concrete actions and synonym triggers.

Suggestions

Lead with 2-3 concrete actions before the preservation goal (e.g. 'Edit, build, and validate the Tiny World Builder single-file app...') to lift specificity.

Add natural synonym triggers a user might say, such as 'tiny world builder', 'Three.js r185 app', or 'single-file builder', to broaden trigger-term coverage.

Tighten the 'what' clause ('preserve the static classic-script Three.js r185 app structure and local edit/reload workflow') into a shorter, scannable capability list.

DimensionReasoningScore

Specificity

The description names a concrete domain (Tiny World Builder repo, tiny-world-builder.html) and a concrete preservation action, but the only action verb is 'preserve ... structure and workflow' — it does not enumerate multiple distinct capabilities, so it falls at anchor 3 ('Names domain and 1-2 concrete actions, but not comprehensive').

3 / 5

Completeness

It answers 'when' explicitly ('Use when editing the Tiny World Builder repo, especially tiny-world-builder.html') and 'what' ('preserve the static classic-script Three.js r185 app structure and local edit/reload workflow'); both are present, though 'what' leans toward a single preservation goal rather than multiple concrete actions, fitting anchor 4 ('Has both what and when; when could be more explicit or specific').

4 / 5

Trigger Term Quality

It opens with a natural trigger ('Use when editing the Tiny World Builder repo') and names the key file 'tiny-world-builder.html', but lacks common synonyms/variations a user might say (e.g. 'tiny world', 'Three.js builder', 'r185') beyond the repo name, placing it at anchor 3 ('Some relevant keywords but missing common variations or synonyms').

3 / 5

Distinctiveness Conflict Risk

The trigger is tightly bound to a specific repo and file ('Tiny World Builder repo', 'tiny-world-builder.html', 'Three.js r185'), creating a clear niche with minimal overlap risk against other skills, matching anchor 5 ('Clear niche with distinct triggers; minimal conflict risk').

5 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.