CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

48

Quality

50%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/redesign-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a comprehensive and opinionated design audit skill with genuinely useful, specific guidance that goes well beyond generic advice. Its main strengths are the breadth of coverage and the specificity of each checklist item (named fonts, exact hex values, concrete CSS properties). Its weaknesses are the lack of executable code examples, missing validation/verification steps in the workflow, and a monolithic structure that could benefit from splitting into referenced sub-files.

Suggestions

Add executable before/after code snippets for the highest-impact fixes (e.g., font swap, color palette cleanup, hover states) so Claude can copy-paste rather than interpret descriptions.

Add explicit validation checkpoints to the workflow: e.g., 'After font swap, verify the font loads by checking Network tab or confirming visual render' and 'After layout changes, test at 320px, 768px, and 1440px widths.'

Split the audit checklist into separate referenced files (e.g., TYPOGRAPHY.md, COLOR.md, LAYOUT.md) with the SKILL.md serving as an overview with links, improving progressive disclosure.

Remove explanatory context Claude already knows (e.g., 'This is an accessibility requirement, not optional' for focus rings, or explaining what iOS Safari viewport bug is) to improve conciseness.

DimensionReasoningScore

Conciseness

The skill is extensive and mostly earns its length through specific, actionable checklist items rather than fluff. However, some items explain things Claude already knows (e.g., what semantic HTML tags are, what 100dvh fixes), and the sheer volume could be tightened—particularly the 'Upgrade Techniques' section which lists aspirational ideas without executable code.

2 / 3

Actionability

The audit checklist is highly specific with concrete CSS properties, values, and named alternatives (fonts, colors, techniques). However, it lacks executable code examples—no complete before/after CSS snippets, no shell commands, no copy-paste-ready implementations. The guidance is concrete in description but stops short of being fully executable.

2 / 3

Workflow Clarity

The 3-step workflow (Scan → Diagnose → Fix) and the 7-step fix priority order provide clear sequencing. However, there are no validation checkpoints—no 'verify the font loaded correctly,' no 'test responsive behavior after layout changes,' no feedback loops for error recovery. For a skill involving potentially destructive UI changes, this is a notable gap.

2 / 3

Progressive Disclosure

The content is well-organized with clear section headers and logical grouping, but it's a monolithic document with no references to external files. At ~250+ lines, sections like the full audit checklist or upgrade techniques could be split into separate reference files. For a standalone skill with no bundle, the internal structure is decent but the length warrants splitting.

2 / 3

Total

8

/

12

Passed

Description

50%

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 communicates a clear intent—upgrading existing web designs to higher quality—but relies on subjective terms like 'premium quality' and 'high-end design standards' without specifying concrete actions. It lacks an explicit 'Use when...' clause, which hurts completeness, and could benefit from more natural trigger terms that users would actually say when requesting design improvements.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to improve the look and feel of an existing website, polish UI design, or fix a generic/AI-generated appearance.'

Include more natural trigger terms users would say, such as 'make it look professional', 'UI polish', 'improve styling', 'redesign', 'looks like AI generated', 'better typography/spacing/colors'.

Replace vague phrases like 'premium quality' and 'high-end design standards' with specific actions, e.g., 'Refines typography, spacing, color palettes, hover states, and visual hierarchy.'

DimensionReasoningScore

Specificity

Names the domain (website/app design upgrades) and some actions (audits, identifies patterns, applies standards), but the actions are somewhat vague—'premium quality' and 'high-end design standards' are subjective and not concrete. It doesn't list specific transformations like 'improves typography, spacing, color palettes, animations.'

2 / 3

Completeness

The 'what' is partially addressed (upgrades design, audits, identifies patterns), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the description of capabilities, which caps this at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Includes some relevant terms like 'websites', 'apps', 'CSS framework', 'vanilla CSS', and 'design', but misses many natural user phrases like 'make it look better', 'UI polish', 'redesign', 'improve styling', 'looks generic', or 'professional design'. The phrase 'generic AI patterns' is somewhat niche.

2 / 3

Distinctiveness Conflict Risk

The focus on upgrading existing designs and identifying 'generic AI patterns' provides some distinctiveness, but terms like 'websites and apps' and 'CSS' are broad enough to overlap with general web development or CSS styling skills. The 'premium quality' angle helps differentiate somewhat but is vague.

2 / 3

Total

8

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
Leonxlnx/taste-skill
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.