Name: clone-website
Rating: 60 (1 reviews)
Author: JCodesMore

Blog Docs Log in Get started

clone-website

Reverse-engineer and clone one or more websites as pixel-perfect replicas

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.roo/skills/clone-website/SKILL.md

The canonical home for this skill is clone-website in JCodesMore/ai-website-cloner-template

Quality

Content

77%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 content is highly actionable with a clear, well-validated workflow, but it is monolithic for its length and carries redundant emphasis between the Guiding Principles and What NOT to Do sections. Splitting the spec template and extraction scripts into bundle files would improve progressive disclosure.

Suggestions

Move the component spec template and the JS extraction scripts into referenced bundle files (e.g. references/spec-template.md, scripts/extract-styles.mjs) and link to them from SKILL.md.

Consolidate the "What NOT to Do" list with the Guiding Principles to remove duplicated guidance on interaction model, layered images, responsive extraction, and smooth scroll.

Trim repetitive emphatic phrasing ("This is not optional", "non-negotiable", "This is NOT optional") where the surrounding imperative already conveys it.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and domain-specific, but the "What NOT to Do" section heavily reiterates the Guiding Principles (interaction model, layered images, responsive, smooth scroll) and there is repeated emphatic padding ("This is not optional", "non-negotiable").	3 / 5
Actionability	It provides copy-paste-ready extraction scripts, a complete component spec template, concrete file paths, and exact commands (npm run build, npx tsc --noEmit) covering the common cases.	5 / 5
Workflow Clarity	The Pre-Flight plus five-phase sequence is clearly ordered with explicit validation checkpoints (build verification, type-check, merge checks) and feedback loops in the Visual QA diff, plus a Pre-Dispatch Checklist.	5 / 5
Progressive Disclosure	The file is well-sectioned but at ~520 lines it inlines content that belongs in separate bundle files (the spec template, two JS extraction scripts, and the Atlas Cloud fallback contract), and no references/scripts/assets exist.	3 / 5
	Total	16 / 20 Passed

Description

65%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 distinctive and uses natural trigger terms, but it lacks an explicit "when to use" clause and only names a couple of concrete actions. Adding a Use-when clause and a few more specific actions would round it out.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to clone, copy, or replicate a website as a pixel-perfect replica."

Broaden action coverage to mention extracting components, assets, and behaviors, not just reverse-engineering and cloning.

Include synonyms such as "copy" or "replicate" to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The phrase "Reverse-engineer and clone one or more websites as pixel-perfect replicas" names the domain and two concrete actions (reverse-engineer, clone) with a quality qualifier, but coverage is not comprehensive (no mention of components, assets, or behaviors).	3 / 5
Completeness	It clearly states the "what" (reverse-engineer and clone websites) but provides no "Use when..." trigger clause, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	"clone", "websites", and "pixel-perfect replicas" are natural terms a user would say, but common synonyms like "copy", "replicate", or "rebuild this site" are missing.	4 / 5
Distinctiveness Conflict Risk	Pixel-perfect website cloning is a clear, narrow niche with distinct triggers and minimal risk of conflicting with other skills.	5 / 5
	Total	15 / 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
skill_md_line_count	SKILL.md is long (526 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: JCodesMore/ai-website-cloner-template
Path: .roo/skills/clone-website/SKILL.md
Commit: 92872bc

Reviewed: 5 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.