CtrlK
BlogDocsLog inGet started
Tessl Logo

url-to-code

Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation.

66

Quality

79%

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 ./packages/opencode/src/skill/builtin/.bundle/product-design/workflows/url-to-code/SKILL.md
SKILL.md
Quality
Evals
Security

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.

An exemplary process-skill body: terse, concrete, and well-sequenced with explicit stop conditions and a gated verification loop. The only improvement space is making the capture and comparison steps slightly more mechanically specific.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and assumes Claude's competence: every sentence is an instruction or constraint ("React is not required", "Build success and server health are not visual verification") with zero padding or explanation of concepts Claude already knows. It matches the 'every token earns its place' anchor.

5 / 5

Actionability

Guidance is mostly concrete and executable for an instruction-only process skill: numbered steps name specific actions ("Capture the full desktop page and a representative mobile viewport", "Run `../design-qa/SKILL.md`, save `design-qa.md`") and enumerate exactly what to inspect. It falls short of 5 because no step gives exact commands, tool invocations, or comparison criteria for the verify pass — those specifics are left implicit.

4 / 5

Workflow Clarity

A clear 10-step sequence with explicit validation checkpoints and feedback loops: step 2 stops on bad surfaces ("Stop if it resolves to a wrong page, login wall, error, unrelated redirect"), step 9 compares against the source, and step 10 gates handoff on "final result: passed" with a fix-mismatch loop. The Hard rules section reinforces the checkpoints.

5 / 5

Progressive Disclosure

At under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist), the skill is a well-organized two-section overview (Workflow, Hard rules) with clearly signaled, one-level-deep pointers to sibling skills (`../index/SKILL.md`, `../design-qa/SKILL.md`) — matching the simple-skill guideline that well-organized sections alone warrant a 5.

5 / 5

Total

19

/

20

Passed

Description

66%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.

A precise, appropriately concise, third-person description that clearly conveys what the skill produces, with good natural trigger vocabulary. Its main weakness is the absence of an explicit "Use when..." clause, which caps completeness and leaves invocation conditions implied rather than stated.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to clone, copy, or faithfully recreate a website or app they own or have permission to reproduce" — this directly addresses the missing 'when' that caps completeness at 3.

Include the natural synonyms users actually say — "clone this site", "copy this page", "turn this URL into code" — to strengthen trigger term coverage beyond "recreate".

Consider naming the boundary (e.g. "for redesign or loosely inspired results, use a different skill") in the description to further reduce overlap with general design/build skills.

DimensionReasoningScore

Specificity

The description states one concrete, well-qualified action — "Recreate an authorized live website or app URL as a faithful, runnable, frontend-only local implementation" — specifying the input (authorized live URL) and the output (faithful, runnable, frontend-only local implementation). It is not several discrete actions like the 5-anchor, but it is more precise than the 1-2 generic actions of the 3-anchor, sitting noticeably above the midpoint.

4 / 5

Completeness

The "what" is clear and specific, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines. When to invoke the skill is only implied by the nature of the action.

3 / 5

Trigger Term Quality

Natural user terms are present: "Recreate", "website", "app", "URL", "frontend". A few common synonyms users would naturally say are missing — notably "clone" (the phrase the body itself uses), "copy", and "rebuild this site" — which keeps it below the comprehensive 5-anchor.

4 / 5

Distinctiveness Conflict Risk

The niche — faithful, frontend-only recreation of a live authorized URL — is distinct from general frontend-building and redesign skills, and the "faithful" / "frontend-only" qualifiers reduce overlap. Minor overlap risk remains with general web-development and design skills, so it does not reach the minimal-conflict 5-anchor.

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
XiaomiMiMo/MiMo-Code
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.