CtrlK
BlogDocsLog inGet started
Tessl Logo

web-design-engineer

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact. Not for back-end, CLI, non-visual coding, source-to-longform article conversion, or narration-driven click-through video presentations.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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 well-engineered, actionable skill body with a clear sequenced workflow, explicit checkpoints, and exemplary progressive disclosure routing to a verified reference bundle. Its only real weakness is verbosity — philosophical and conceptual exposition that Claude largely already knows could be trimmed to improve token efficiency.

Suggestions

Trim conceptual/philosophical exposition Claude already knows — e.g., the anti-cliché "reasoning chain" (#1-3) and the prose in "Aim to Stun" / "Avoid AI-Style Clichés (the WHY matters)" — keeping only the actionable rules and the table.

Consolidate the repeated design-philosophy rationale ("less is more", "the bar is stunning not functional") into a single short principles block instead of restating across Scope, Core philosophy, Content Principles, and Aim to Stun.

Move the longer anti-cliché taxonomy detail entirely into references/failure-patterns.md and keep only the hard-rule summary inline, since the body already routes deeper detail there.

DimensionReasoningScore

Conciseness

The ~490-line body is mostly efficient and actionable, but contains conceptual exposition Claude largely already knows (the anti-cliché "reasoning chain", "Aim to Stun" prose, repeated design-philosophy rationale) that could be tightened; it sits above the verbose anchor but below the lean ideal.

2 / 3

Actionability

Highly executable guidance throughout — a copy-paste Design Read YAML block, a design-system declaration template, the Pre-delivery Checklist with specific checks, pinned CDN URLs, and concrete hard rules (no scrollIntoView, no const styles = {}, >1000-line split threshold), matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clearly sequenced Step 0→Step 7 workflow with explicit 🛑 Checkpoints 1/2/3, feedback loops (verify facts → ask if ambiguous), and a self-check checklist matches the anchor for clear sequence with explicit validation steps and error-recovery loops.

3 / 3

Progressive Disclosure

The body is an overview that routes to one-level-deep reference files (advanced-patterns.md, failure-patterns.md, style-recipes/INDEX.md, etc.) via a dedicated References Routing table with explicit "read on demand" guidance; all referenced paths were verified to exist as real bundle files.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, uses natural third-person trigger language, explicitly answers both what and when, and sharply scopes its niche with explicit exclusions. It is a model of the strong examples in the rubric.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Build or redesign polished browser-rendered visual artifacts") and enumerates seven specific output types (pages, dashboards, prototypes, slide decks, animations, UI mockups, data visualizations), matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly answers both what ("Build or redesign polished browser-rendered visual artifacts...") and when (explicit "Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA" clause), matching the anchor requiring both with explicit triggers.

3 / 3

Trigger Term Quality

Natural user-facing phrases are well covered — "visual front-end creation", "design-system exploration", "design critique", "browser acceptance / QA" — alongside concrete artifact names, giving good coverage of terms users would actually say.

3 / 3

Distinctiveness Conflict Risk

A clear visual-front-end niche is reinforced by an explicit "Not for back-end, CLI, non-visual coding, source-to-longform article conversion, or narration-driven click-through video presentations" exclusion, making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 7 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
ConardLi/garden-skills
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.