web-clone

网站复刻 / 克隆方法论。USE WHEN 用户说复刻网站、克隆网站、clone website、抄个站、仿站、照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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.

The body is highly actionable and rigorously sequenced with strong validation gates, and it practices clean progressive disclosure via verified one-level-deep references. Its only real weakness is verbosity in the rationale and paradigm-explanation passages, which could be trimmed without losing clarity.

Suggestions

Tighten the marbles refraction-paradigm paragraph (lines 244-247) to a one-line pointer to references/marbles-case.md; the detailed architecture belongs in the reference, not the overview.

Compress the OpenDesign environment-prep paragraph (lines 34-35) into a short bullet list — the CDP/Chromium rationale is context Claude can infer from the script names.

Move the extended '为什么不许降级成视觉复刻' justification (line 117) into references/assessment.md and keep only the default-mode rule inline, preserving the discipline without the prose.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense and decision-oriented, but several passages over-explain what Claude already knows — the marbles refraction paradigm walkthrough, the OpenDesign CDP environment-prep paragraph, and the '为什么不许降级' rationales — pulling it to the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Every step ships copy-paste-ready bash commands with flags, expected artifacts, and concrete URLs (e.g. recon-site.mjs --url/--out/--label, audit-clone.mjs --recon --strict), fully covering the common cases.	5 / 5
Workflow Clarity	A numbered Step 0–6 sequence with explicit validation gates and feedback loops — 'audit exit 2 修完重跑，不通过不许交付', mandatory browser verification, and recon→compare→visual-diff re-run — matches the explicit-checkpoints-with-error-recovery anchor.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references (references/.md and scripts/.mjs), all verified to exist, plus an '内置脚本' catalog mapping each script to its detail file — content is appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: it states concrete actions, enumerates comprehensive natural trigger terms in both languages, and explicitly pairs 'what' with 'when'. It occupies a clear, low-conflict niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容) as a portable decision tree and explicitly covers three branches (静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站), matching the comprehensive-coverage anchor.	5 / 5
Completeness	It states a clear 'what' (复刻方法论 + 可移植决策树 + 三大分支) and an explicit 'when' via 'USE WHEN 用户说…' with concrete trigger phrases, satisfying both halves explicitly.	5 / 5
Trigger Term Quality	The 'USE WHEN 用户说…' clause enumerates comprehensive natural synonyms in both Chinese and English (复刻网站、克隆网站、clone website、抄个站、仿站、reproduce site) plus tech-specific triggers (WebGL/Canvas/Three.js), matching the full-synonym-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	The website-cloning niche is sharply defined with distinct bilingual triggers and a unique真源码-first discipline, giving minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 6 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: skills/web-clone/SKILL.md
Commit: d4138ea

Reviewed: 3 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.