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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/web-design-guidelines/SKILL.md

Quality

Content

71%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 skill body is a lean, well-structured instruction-only adapter that delegates the actual rules to a fetched source. Its main weakness is redundant sequencing between the 'How It Works' and 'Usage' sections, which slightly hurts conciseness and workflow clarity.

Suggestions

Merge 'How It Works' and 'Usage' into a single workflow, or have 'Usage' reference the steps rather than re-listing them, to remove the duplicated fetch-read-apply-output sequence.

State explicitly that the audit is read-only (no file modification) so Claude knows no validation/rollback step is required, which sharpens workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but 'How It Works' and 'Usage' duplicate the same fetch-read-apply-output sequence almost verbatim, so it lands at 'mostly efficient but could be tightened' rather than the minor-trim anchor at 4.	3 / 5
Actionability	Provides a concrete source URL, names the exact tool ('Use WebFetch'), and specifies the output format ('file:line'); as an instruction-only skill whose rules are fetched at runtime, the absence of inline code is justified, matching 'mostly executable guidance; minor gaps' rather than the incomplete-pseudocode anchor at 3.	4 / 5
Workflow Clarity	The review flow is clearly sequenced (fetch -> read -> check -> output) and the operation is a read-only audit requiring no validation checkpoint, but the duplicated two-section workflow introduces minor muddiness, fitting 'clear sequence with most checkpoints present' rather than the simple-skill 5.	4 / 5
Progressive Disclosure	The body is under 50 lines, needs no external reference files, and is organized into clearly labeled sections (How It Works, Guidelines Source, Usage), meeting the simple-skill exception for a 5; the single one-level reference to a sibling skill is well-signaled.	5 / 5
	Total	16 / 20 Passed

Description

86%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 well-formed: it answers what and when with concrete, natural trigger phrases in third-person voice. Its only weakness is that the 'what' names a single review action rather than enumerating several specific capabilities.

Suggestions

List 2-3 concrete review capabilities (e.g., 'check accessibility, layout consistency, and interaction patterns') in the 'what' clause to raise specificity.

Tighten the overlap-prone triggers ('audit design', 'review UX') by scoping them to the Web Interface Guidelines standard to reduce conflict with general design skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Web Interface Guidelines compliance') and one concrete action ('Review UI code for compliance') but does not enumerate several distinct actions, fitting the 'domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor at 4.	3 / 5
Completeness	Explicitly states both what it does ('Review UI code for Web Interface Guidelines compliance') and when to use it ('Use when asked to...') with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	Lists five natural trigger phrases a user would actually say ('review my UI', 'check accessibility', 'audit design', 'review UX', 'check my site against best practices'), matching the comprehensive-synonyms anchor; it does not fall to 4 because coverage of common phrasings is broad.	5 / 5
Distinctiveness Conflict Risk	Targets a specific external standard with distinct triggers, but broad phrases like 'audit design' and 'review UX' create minor overlap with general design-review skills, so it sits at 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor at 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/web-design-guidelines/SKILL.md
Commit: fe6d8de

Reviewed: 8 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.