build-games-and-playful-experiences

构建、重构、诊断和验证以玩家能动性为核心的二维游戏与趣味体验。用于二维规则/动作/益智游戏、互动玩具、叙事探索、节奏体验、生成体验和本地多人；按子型选择专业运行时与内容工具，分别验证机制、手感、内容、音频、可访问性、平台和玩家价值，且不以工程通过冒充好玩、公平或复玩价值。

Quality

88%

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

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.

A highly structured, validation-driven skill body with clear routing, per-domain gates, and explicit feedback loops, supported by well-signaled one-level-deep reference files. It is slightly denser than the leanest conciseness anchor and stops just short of fully copy-paste-ready actionability.

Dimension	Reasoning	Score
Conciseness	Dense, prescriptive prose that assumes Claude's intelligence and never pads with basic game-development concepts; minor passages (e.g. the feel/UI decoration rules) could be tightened further, keeping it just below the lean score-5 anchor.	4 / 5
Actionability	Each of the eight gates specifies concrete inputs/actions/evidence/ceiling/failure-return, and tool routing references real profiles with hash/probe procedures; mostly executable guidance with minor gaps in copy-paste-ready specifics.	4 / 5
Workflow Clarity	Clear sequenced routing (Create/Edit/Diagnose), two locked contracts up front, and per-gate explicit validation with feedback loops and failure returns ("失败返回", "只有...才") for destructive/batch operations, matching the score-5 anchor.	5 / 5
Progressive Disclosure	SKILL.md is an overview with bulk detail split into two well-signaled, one-level-deep references ([工具能力档案](references/tool-profiles.md) and [领域模式](references/patterns.md)), both real files, matching the score-5 anchor.	5 / 5
	Total	18 / 20 Passed

Description

92%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 dense, third-person, well-scoped description that clearly states what it does, when to use it, and what it deliberately does not claim. Trigger term coverage is strong but stops short of the synonym/extension breadth of the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "构建、重构、诊断和验证", "按子型选择专业运行时与内容工具", and seven named verification domains (机制、手感、内容、音频、可访问性、平台和玩家价值) — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what (build/refactor/diagnose/verify 2D games) and when via the "用于..." clause enumerating concrete triggers, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural subtype trigger phrases users would say (二维规则/动作/益智游戏、互动玩具、叙事探索、节奏体验、生成体验和本地多人) are well covered, but it lacks file-extension/synonym equivalents that the score-5 anchor expects.	4 / 5
Distinctiveness Conflict Risk	Clear niche (2D games centered on player agency) with explicit non-goals ("不以工程通过冒充好玩、公平或复玩价值") and routing of 3D/web to other skills gives minimal conflict risk.	5 / 5
	Total	19 / 20 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: EverMind-AI/Raven
Path: plugins-dist/design-engine/raven_design/skills/build-games-and-playful-experiences/SKILL.md
Commit: e6c0344

Reviewed: 1 day 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.