CtrlK
BlogDocsLog inGet started
Tessl Logo

web-clone

Web Clone deprecated shim

45

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/web-clone/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 detailed, well-sequenced multi-pass workflow with executable scripts, strong validation/feedback loops, and a final checklist — excellent on workflow clarity and actionability. Its weaknesses are length/redundancy (conciseness) and a fully monolithic structure with no progressive disclosure to separate reference files.

Suggestions

De-duplicate the composite verdict JSON (shown in both Pass 4 and Output_Contract) by defining it once and referencing it, and tighten Scope_Limits/Example to cut tokens.

Move the two long browser_evaluate extraction scripts and the Output_Contract schema into reference files under references/ and link to them, improving progressive disclosure for this large skill.

The Prerequisites section numbering starts at '2.' with no item 1 — fix the list so the required-tools setup reads as a coherent sequence.

DimensionReasoningScore

Conciseness

The body is mostly concrete and earned, but it is long (~350 lines) with redundant material — the composite verdict JSON appears in both Pass 4 step 5 and the Output_Contract section — and sections like Scope_Limits and the worked Example could be trimmed; it fits 'mostly efficient but could be tightened' rather than 4 (only minor trimming needed).

3 / 5

Actionability

It provides copy-paste-ready JavaScript extraction scripts explicitly marked 'COPY THIS SCRIPT EXACTLY' plus concrete shell commands (`npx serve`, `python3 -m http.server`), but Pass 2 and Pass 3 are higher-level descriptive guidance without executable code, leaving minor gaps that keep it below a 5.

4 / 5

Workflow Clarity

The five-pass workflow (Extract, Build Plan, Generate, Verify, Iterate) is clearly sequenced with explicit validation checkpoints in Pass 4 (visual score >= 85, landmark match, functional spot-check) and a fix-re-verify feedback loop in Pass 5 capped at 5 iterations, plus a Final_Checklist — matching the 'clear sequence with explicit validation steps and feedback loops' anchor.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent) and all content — including long extraction scripts, the output contract, and a worked example — is inlined in one ~350-line file; it has section structure via pseudo-XML tags but content that would benefit from being split into separate files is inline, fitting 'some structure but could be better organized' rather than 4.

3 / 5

Total

15

/

20

Passed

Description

23%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 far too terse for a usable skill description: it conveys only that this is a deprecated web-clone shim with no concrete actions, no natural trigger phrasing, and no explicit use-when guidance. It is distinct enough by niche but fails on specificity, trigger terms, and completeness.

Suggestions

Even for a deprecated shim, state concrete capabilities in third person (e.g. 'Clones a single live web page's layout, styling, and interactions into a local project') so the what is unambiguous.

Add an explicit trigger clause such as 'Use when the user provides a live URL to clone; do not use for screenshot-only or multi-page requests' to address completeness.

Include natural trigger terms users would say ('clone this page', 'recreate this website', 'web page clone') instead of the technical label 'deprecated shim'.

DimensionReasoningScore

Specificity

The description 'Web Clone deprecated shim' states the domain but lists no concrete actions or capabilities whatsoever, matching the 'entirely vague; no concrete actions' anchor; it does not rise to a 2 because that anchor requires at least a minimal generic action verb (e.g. 'Processes PDF files').

1 / 5

Completeness

It gives only a vague 'what' (a deprecated shim for web cloning) and entirely omits any 'when' / 'Use when...' trigger guidance, which the rubric caps at 3; it is above 1 because a vague what is present, but not at 3 since there is no clear actionable what.

2 / 5

Trigger Term Quality

'Web Clone' is one relevant keyword a user might say, but the surrounding phrase 'deprecated shim' is technical jargon and the natural trigger phrases users would actually say are missing, fitting the 'one or two generic keywords' anchor rather than 1 (no keywords) or 3 (broader coverage).

2 / 5

Distinctiveness Conflict Risk

'Web Clone' names a reasonably specific niche, but the description is terse and the body reveals overlap with related visual skills ($visual-ralph, $visual-verdict), so it is 'somewhat specific but could still overlap with similar skills' rather than clearly distinct (4).

3 / 5

Total

8

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Yeachan-Heo/oh-my-codex
Reviewed

Table of Contents

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.