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

96%

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

92%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 a tightly organized, highly actionable methodology with strong workflow sequencing, validation feedback loops, and well-signaled one-level-deep references. Its only weakness is moderate verbosity from repeated prescriptive/emphatic prose that could be condensed.

Suggestions

Consolidate the recurring "不许因为…就…" discipline clauses into a single rules block; restating the same prohibition in multiple sections adds tokens without adding guidance.

The 「实证（marbles 案例）」 paragraph and the 位移图折射 DOM advanced-paradigm note overlap with references/marbles-case.md and references/reverse-engineering.md — consider shortening the inline versions to one-line pointers.

Trim the 内置脚本 list entries to one-line role descriptions since the decision-tree steps already show each script's invocation and flags.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence (no explaining of what WebGL/Playwright is), with mostly high-signal guardrails, but the body is long and carries repeated emphatic discipline prose ("不许…就…") that could be trimmed. Not a 5 because some rhetorical enforcement could be tightened without losing meaning.	4 / 5
Actionability	Provides copy-paste-ready, fully-flagged bash commands (node scripts/recon-site.mjs --url … --out … --label …, gh api search, curl raw) and concrete scripts covering the common clone cases across all branches.	5 / 5
Workflow Clarity	Explicitly sequenced decision tree (Step 0–6, "按顺序走，不许跳") with validation checkpoints and feedback loops: 浏览器真验证, audit-clone.mjs --strict exit 2 → 修完重跑 → 不通过不许交付, and post-clone compare/visual-diff recon.	5 / 5
Progressive Disclosure	SKILL.md holds the decision tree and core rules while farming out deeper detail to one-level-deep references (assessment.md, design-dna.md, effect-extraction.md, static-mirror.md, etc.), all clearly signaled inline and verified to exist as real files.	5 / 5
	Total	19 / 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 concrete, trigger-rich, and explicitly pairs what the skill does with when to invoke it, using third-person voice throughout. It is comprehensive across specificity, triggers, completeness, and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions forming a portable decision tree (「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」), explicitly covering three branches (静态站 / React-Vue-Next / WebGL-Canvas).	5 / 5
Completeness	Explicitly answers both 'what' (提供可移植决策树，覆盖三大分支，强制核对 AI 二手代码) and 'when' (USE WHEN 用户说… with concrete trigger phrases).	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrases including synonyms (复刻网站、克隆网站、clone website、抄个站、仿站) and technology names (WebGL/Canvas/Three.js) users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (website cloning) with distinct, specific triggers (复刻/克隆/仿站/clone website) that are unlikely to fire for unrelated skills; minimal conflict risk.	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: 1a7a23d

Reviewed: about 3 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.