clone-website

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

Quality

69%

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 ./.cline/skills/clone-website/SKILL.md

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 body is highly actionable with a clear, well-validated workflow and concrete code, but it is over-long with repeated guidance and keeps substantial reference material inline instead of splitting it into bundled files. Trimming repetition and externalizing the scripts/template would improve it.

Suggestions

Move the extraction scripts, the component spec template, and the Atlas Cloud API contract into separate files under references/ and link to them, reducing the inline wall of text.

Consolidate the repeated guidance about interaction models, smooth-scroll libraries, and layered images so each point is stated once; remove the overlap between 'Guiding Principles' and 'What NOT to Do'.

Trim the 'What NOT to Do' section to items not already covered in the phased workflow to cut redundancy.

Dimension	Reasoning	Score
Conciseness	Content is skill-specific and mostly purposeful, but at ~520 lines it repeats the same lessons (interaction model, smooth-scroll libraries, layered images) across the Guiding Principles, Phases, and 'What NOT to Do' sections, so it could be tightened noticeably.	3 / 5
Actionability	Provides copy-paste-ready JavaScript extraction scripts, exact file paths, concrete commands (npm run build, npx tsc --noEmit), a complete spec template, and exact Atlas Cloud API endpoints — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced Pre-Flight → Phase 5 pipeline with explicit validation checkpoints, feedback loops (QA diff → re-extract → update spec → fix), and a Pre-Dispatch Checklist, fully covering the destructive/batch operations involved.	5 / 5
Progressive Disclosure	Internally well-organized with clear headers, but it is a single monolithic file with no external references, and large blocks (extraction scripts, spec template, Atlas Cloud contract) are inlined rather than split into separate reference files.	3 / 5
	Total	16 / 20 Passed

Description

61%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 specific and distinctive, clearly naming a concrete niche, but it omits any 'Use when...' trigger guidance and lists only two high-level actions. Adding a trigger clause and a few more concrete actions would raise completeness and specificity.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user wants to clone, copy, or recreate a website as a pixel-perfect replica.'

List a few more concrete actions to broaden specificity, such as extracting styles, downloading assets, and rebuilding the page as components.

Include common synonyms users might say (copy, recreate, rebuild, mirror a site) to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the website domain and two concrete verbs ('Reverse-engineer and clone') with a 'pixel-perfect replicas' modifier, but coverage is not comprehensive (no screenshots, assets, components, or QA). Matches anchor 3; not 4 because it lacks 'several specific actions'.	3 / 5
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3 — matching the anchor for a clear 'what' with 'when' missing.	3 / 5
Trigger Term Quality	Includes natural keywords users would say ('clone', 'websites', 'pixel-perfect', 'replica', 'reverse-engineer'); a few common synonyms (recreate, copy, rebuild, mirror) are missing, so it sits at anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (cloning sites as pixel-perfect replicas) with minimal conflict risk, but lacks explicit trigger phrases that would fully distinguish it from general web-build skills, placing it at anchor 4 rather than 5.	4 / 5
	Total	14 / 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: .cline/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.