threejs-qa-release

Verify and release Three.js browser games. Combines playtest QA, automated bot playtests, mobile/responsive checks, production builds, preview verification, static-hosting base paths, debug gating, bundle review, screenshots, visual test harness decisions, packaged canvas-pixel inspection with measured metrics, console checks, and release risk reports.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-3

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

The body is lean, actionable, and well-structured: it gives executable commands with concrete flags, two sequenced workflows with explicit validation gates, and a concise overview that clearly routes to one-level-deep, verified reference files.

Dimension	Reasoning	Score
Conciseness	The ~55-line body is dense and directive with no concept-tutoring ('Install dependencies if needed', 'Run build/typecheck') and assumes Claude's competence; every reference-loading sentence earns its place by naming the exact load condition, matching the lean-and-efficient anchor and not score 2's 'some unnecessary explanation'.	3 / 3
Actionability	Provides a fully executable command ('node <this-skill-dir>/scripts/inspect-threejs-canvas.mjs --url http://127.0.0.1:5188') with concrete flags (--mobile, --state, --seed) and the named hook '__THREE_GAME_TEST_HOOKS__', plus exact artifact paths and named metrics, matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	Two clearly numbered sequences (QA Workflow 1-12, Release Workflow 1-6) with explicit validation gates — 'Do not mark QA/release complete while this reference is skipped', 'over-budget rows need a documented tradeoff', 'blank-canvas or error conditions still exit nonzero' — and a pass/fail-led final response, matching the explicit-checkpoints anchor.	3 / 3
Progressive Disclosure	Concise overview body signals one-level-deep references by full path with the exact condition for loading each ('Load references/checklists/visual-verification.md for screenshot/canvas verification...'), and all referenced bundle files were verified present, matching the well-signaled one-level-deep anchor; not score 2 because navigation is explicit and organized.	3 / 3
	Total	12 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 and well-differentiated for a clear niche, but reads as a capability inventory and omits an explicit 'Use when...' trigger clause, capping completeness and leaving trigger-term quality below the top level.

Suggestions

Add an explicit 'Use when...' trigger clause naming how users would phrase the request (e.g., 'Use when verifying, playtesting, or releasing a Three.js browser game, or when the user asks for QA, screenshots, or a production build of a 3D game').

Lead the description with a tighter capability summary and move the long action inventory behind natural trigger phrasing so trigger-term quality reaches common-user variations like 'QA a Three.js game', 'release a WebGL game', 'mobile check a 3D game'.

Dimension	Reasoning	Score
Specificity	Enumerates many concrete actions — 'playtest QA, automated bot playtests, mobile/responsive checks, production builds, ... packaged canvas-pixel inspection with measured metrics, console checks, and release risk reports' — matching the multiple-specific-actions anchor; not score 2 because the list is comprehensive and concrete rather than partial.	3 / 3
Completeness	Clearly states what ('Verify and release Three.js browser games. Combines...') but has no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 2; above score 1 because the what is clearly present.	2 / 3
Trigger Term Quality	Contains some natural terms ('Three.js browser games', 'playtest', 'screenshots', 'release', 'mobile') but is structured as a capability inventory rather than natural trigger variations a user would say, falling short of score-3 keyword coverage; above score 2's single-generic-keyword bar because several relevant terms are present.	2 / 3
Distinctiveness Conflict Risk	'Three.js browser games' QA and release is a clear, narrow niche unlikely to trigger the wrong skill, matching the distinct-triggers anchor; not score 2 since it is far more specific than a generic file-type/domain description.	3 / 3
	Total	10 / 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
referenced_paths_exist	Referenced path issues: 5 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: majidmanzarpour/threejs-game-skills
Path: skills/threejs-qa-release/SKILL.md
Commit: 7221c1f

Reviewed: 13 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.