CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

The canonical home for this skill is web-design-guidelines in majiayu000/claude-skill-registry

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A tight, actionable instruction-only skill whose guidance (exact URL, named tools, output format, fallback) is concrete and executable. The two real weaknesses are a near-duplicate step list across "How It Works" and "Usage", and the absence of any fetch-failure handling.

Suggestions

Merge "How It Works" and "Usage" into one workflow section and let the argument-handling note cover only the 'no files specified' fallback, removing the duplicated fetch/read/apply/output steps.

Add a brief error-recovery checkpoint, e.g. "If WebFetch fails or returns an error page, tell the user and ask whether to proceed with your built-in best-practices knowledge instead".

Show one example findings line in the `file:line` output format so the expected result shape is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no concept explanations, but the four-step workflow (fetch → read → apply → output) is repeated nearly verbatim in both "How It Works" and "Usage", and "The fetched content contains all the rules and output format instructions" is filler. This matches 'efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Concrete guidance throughout: an exact fetch URL, a named tool ("Use WebFetch"), a defined output format ("terse `file:line` format"), and a specific fallback tool ("mcp-feedback-enhanced (e.g., `ask_followup_question`)"). Minor gaps — no example WebFetch invocation and no instruction for what to do if the fetch fails or returns an error page — keep it below anchor 5.

4 / 5

Workflow Clarity

The numbered fetch/read/check/output sequence is clear and coherent, and this is a read-only review task so the destructive/batch validation cap does not apply. However, there is no checkpoint for fetch failure or partial guideline retrieval, matching 'clear sequence with most checkpoints; minor validation gaps' rather than the explicit error-recovery anchor 5.

4 / 5

Progressive Disclosure

At 37 lines with no bundle files and no need for external references, the skill qualifies for the simple-skill provision: sections (How It Works, Guidelines Source, Usage) are well-organized and the only pointer (the guidelines URL) is clearly signaled. Structure is clear and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

78%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 strong description with a clear third-person capability statement and an explicit, well-phrased trigger clause. Its main weakness is specificity: the actual scope of the guidelines review (accessibility, semantics, forms, etc.) is left implicit.

Suggestions

Enumerate concrete capability actions instead of one umbrella action, e.g. "Check UI code for accessibility, semantics, forms, and performance compliance with the Web Interface Guidelines".

Mention the file types in scope (HTML, JSX/React components, CSS) in the 'what' clause so users can tell whether their stack qualifies.

Add one or two missing natural trigger variations such as "design review" or "usability" to broaden keyword coverage.

DimensionReasoningScore

Specificity

"Review UI code for Web Interface Guidelines compliance" names the domain and one concrete action, but the description never enumerates what the review covers (accessibility, semantics, forms, performance), matching the '1-2 concrete actions, not comprehensive' anchor. It falls below anchor 4 because the specific check categories only appear indirectly as trigger phrases, not as stated capabilities.

3 / 5

Completeness

The description explicitly answers "what" ("Review UI code for Web Interface Guidelines compliance") and "when" ("Use when asked to...") with concrete quoted trigger phrases, exactly matching the anchor for clearly and explicitly answering both. It is above anchor 4 because the 'when' clause is not merely present but enumerates specific trigger phrases.

5 / 5

Trigger Term Quality

Quoted triggers "review my UI", "check accessibility", "audit design", "review UX", and "check my site against best practices" are natural phrases users would actually say, spanning the review/check/audit verbs. A few common variations ("design review", "usability", "a11y", "frontend best practices") are missing, which keeps it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

The "Web Interface Guidelines compliance" framing carves out a clear niche, but generic triggers like "check accessibility" or "audit design" could plausibly fire for a general code-review or accessibility-specific skill. This matches 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor 5.

4 / 5

Total

16

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

majiayu000/claude-skill-registry-data

Path

data/02-designer-webguidelines/SKILL.md

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.