redesign-existing-projects

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/redesign-skill/SKILL.md

Quality

Content

80%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 a strong, highly actionable audit checklist with concrete fixes throughout and a clear workflow sequence. Its main weakness is structure: it is a single long file with no external reference files, which limits progressive disclosure even though the in-file organization is good.

Suggestions

Split the detailed audit checklists (Typography, Color, Layout, etc.) into a separate reference file (e.g., references/audit-checklist.md) and have SKILL.md summarize the workflow and point to it, improving progressive_disclosure.

Add explicit inline validation checkpoints in the Scan -> Diagnose -> Fix workflow (e.g., 'After each Fix step, reload the page and confirm no functionality broke') to move workflow_clarity to 5.

Trim the longest layout and interactivity bullets to their core problem+fix pair to push conciseness toward 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and action-oriented with almost no concept-padding (no 'what a font is' or 'how CSS works'); a few longer layout/interactivity bullets could be trimmed, but it is efficient above the midpoint.	4 / 5
Actionability	Every bullet pairs a named problem with a concrete, executable fix (specific font names, hex values, CSS properties, viewport units, and a real placeholder URL), covering the common cases copy-paste ready.	5 / 5
Workflow Clarity	A clear Scan -> Diagnose -> Fix sequence is paired with a prioritized Fix Priority ordering and rules; the operations are not destructive/batch so the strict cap does not apply, but explicit validation checkpoints ('test after every change') are framed as rules rather than inline steps, leaving a minor gap versus the explicit-checkpoint anchor at 5.	4 / 5
Progressive Disclosure	Sections are well-organized, but the entire skill is a single monolithic SKILL.md with no bundle files in references/scripts/assets and no external links, so there is no file-level progressive disclosure; the structure-only organization sits at the 'some structure' anchor rather than a split-file 4/5.	3 / 5
	Total	16 / 20 Passed

Description

57%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 action-oriented with a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps completeness at 3 and leaves trigger-term coverage incomplete. Adding a concrete trigger sentence would lift it into the 4-5 range.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks to redesign, modernize, or improve the look of an existing website or app').

Include user-facing synonyms like 'redesign', 'modernize', 'make it look premium', or 'fix the design' alongside the technical terms to improve trigger-term coverage.

Tighten the scope claim ('Works with any CSS framework or vanilla CSS') so it reads as a constraint rather than a broad capability that risks overlap.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Upgrades existing websites and apps', 'Audits current design', 'identifies generic AI patterns', 'applies high-end design standards') rather than vague language, with only minor gaps in coverage.	4 / 5
Completeness	Has a clear 'what' (upgrade/audit/identify/apply) but no explicit 'Use when...' trigger clause; per the guidelines a missing 'when' caps completeness at 3 even though the 'what' is strong.	3 / 5
Trigger Term Quality	Mentions 'websites', 'apps', 'CSS framework', 'vanilla CSS' which are domain-relevant, but misses the natural phrases a user would actually voice (e.g., 'redesign', 'make it look better', 'modernize'). Notably below the comprehensive-coverage anchor at 5 but above a single generic keyword at 2.	3 / 5
Distinctiveness Conflict Risk	Targets a fairly specific niche (redesigning existing projects rather than building new), which limits overlap; minor risk of collision with general UI/design skills, keeping it below 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Leonxlnx/taste-skill
Path: skills/redesign-skill/SKILL.md
Commit: ccbc156

Reviewed: 10 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.