web-games

Web browser game development principles. Framework selection, WebGPU, optimization, PWA.

Quality

53%

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 ./.agents/skills/game-development/web-games/SKILL.md

Quality

Content

50%

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

The content is well-structured and refreshingly lean, but it functions as a reference sheet of principles rather than actionable guidance: no executable examples, time-sensitive version data that will date quickly, and no progressive split into deeper reference files. Adding concrete code snippets and moving version-specific detail into a versioned reference would lift the mid-tier scores.

Suggestions

Move time-sensitive version/share data (browser support versions, framework versions, ~73% figure) into a separate versioned reference file or a clearly marked 'current support' section, and keep the body version-agnostic.

Add at least one small executable snippet per major topic (e.g., a navigator.gpu feature-detection block and a minimal AudioContext resume handler) to reach copy-paste-ready actionability.

Split the larger reference tables (framework comparison, browser support, asset formats) into one-level-deep reference files linked from the overview to improve progressive disclosure for this >50-line skill.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and terse bullets with no concept padding, but it embeds time-sensitive version and share data (Chrome v113, Firefox v131, Safari 18.0, ~73% global, Phaser 4, PixiJS 8, Babylon.js 7) outside any deprecated section, which the guidelines penalize.	2 / 3
Actionability	Concrete specifics exist ('Check navigator.gpu', 'KTX2, Draco, WebP', 'Create AudioContext on first click/tap') plus a framework decision tree, but there is no executable code or worked example, leaving the guidance reference-oriented rather than copy-paste ready.	2 / 3
Workflow Clarity	Sections are well organized and the framework decision tree gives clear sequencing, but there is no cohesive multi-step workflow with explicit validation checkpoints; the guidance is a collection of principles rather than a sequenced process.	2 / 3
Progressive Disclosure	The body is a single monolithic ~150-line file with all content inline and no bundle files; the numbered sections provide structure, but the under-50-line exception does not apply and detail that could live in separate references is not split out.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 identifies a clear, distinctive niche and lists relevant concrete topics, but it reads as a topical noun list rather than concrete actions and lacks any explicit 'Use when' trigger guidance. Adding trigger phrasing and verb-based capabilities would raise it across specificity, trigger quality, and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when building HTML5/canvas/browser games, or when the user mentions WebGPU, PWA, or game framework choice').

Reframe the capability list as concrete actions instead of noun topics (e.g., 'Select game frameworks, adopt WebGPU with fallback, optimize assets, package as a PWA').

Include common user variations such as 'HTML5 game', 'canvas game', and 'JavaScript game' alongside 'web browser game'.

Dimension	Reasoning	Score
Specificity	The description lists concrete topical areas ('Framework selection, WebGPU, optimization, PWA') but frames them as noun-phrase topics under the abstract word 'principles' rather than explicit verbs like extract/fill/merge, so it names the domain and some actions but is not fully concrete.	2 / 3
Completeness	It states what the skill covers but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes genuine natural terms ('WebGPU', 'PWA', 'web browser game'), but 'Framework selection' and 'optimization' are process labels rather than user utterances and common variations like 'HTML5 game' or 'canvas game' are missing.	2 / 3
Distinctiveness Conflict Risk	'Web browser game development' with distinct technical triggers (WebGPU, PWA) carves a clear niche that is unlikely to fire for unrelated or general web-development skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/game-development/web-games/SKILL.md
Commit: 04514f0

Reviewed: about 12 hours 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.