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".
76
69%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/web-design-guidelines/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with a clear 'Use when' clause containing multiple natural trigger phrases, which is its strongest aspect. The main weakness is that the 'what' portion is somewhat vague—it says 'review UI code for compliance' but doesn't enumerate the specific checks or actions performed. There's also moderate overlap risk with other accessibility or design review skills.
Suggestions
Add 2-3 specific concrete actions to the 'what' portion, e.g., 'Checks color contrast, validates semantic HTML, audits keyboard navigation, and reviews responsive design patterns against Web Interface Guidelines.'
Differentiate from general accessibility or UX review skills by mentioning the specific guideline set or unique aspects this skill covers that others don't.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (UI code review) and the standard (Web Interface Guidelines compliance), but doesn't list specific concrete actions like 'check color contrast', 'validate ARIA labels', 'audit navigation patterns', etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (review UI code for Web Interface Guidelines compliance) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes multiple natural trigger phrases users would actually say: 'review my UI', 'check accessibility', 'audit design', 'review UX', 'check my site against best practices'. These cover a good range of natural user language. | 3 / 3 |
Distinctiveness Conflict Risk | While 'Web Interface Guidelines compliance' is somewhat specific, terms like 'check accessibility', 'audit design', and 'review UX' could overlap with general accessibility audit skills, design system skills, or broader code review skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a thin wrapper that delegates all substantive logic to an externally fetched document. While it's well-organized and concise in structure, it's redundant internally (repeating the same steps twice) and lacks actionability since it provides no concrete examples, fallback behavior, or validation steps. The skill's value depends entirely on the availability and stability of the external URL.
Suggestions
Remove the redundancy between 'How It Works' and 'Usage' sections — consolidate into a single workflow section to improve conciseness.
Add a fallback or error handling step for when the URL fetch fails (e.g., 'If fetch fails, inform the user and suggest they provide the guidelines manually').
Include a brief example of expected output format (e.g., a sample `file:line` finding) so the skill is partially actionable even without the fetched content.
Add a validation checkpoint after fetching the guidelines to confirm the content was retrieved successfully before proceeding with the review.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but has some redundancy — the 'How It Works' and 'Usage' sections largely repeat the same 4-step process. The instruction to fetch guidelines is stated three times across different sections. | 2 / 3 |
Actionability | It provides a concrete URL to fetch and mentions using WebFetch, but the actual review logic is entirely delegated to the fetched content. There's no concrete code, no example output, and no fallback if the URL is unreachable. The skill essentially says 'fetch this URL and do what it says.' | 2 / 3 |
Workflow Clarity | Steps are listed but there's no validation or error handling — what if the fetch fails? What if the fetched content format changes? There's no checkpoint for verifying the guidelines were successfully retrieved before proceeding with the review. | 2 / 3 |
Progressive Disclosure | For a simple skill with no bundle files, the content is appropriately short and well-organized into clear sections. The external reference (the URL) is one level deep and clearly signaled. No need for additional files given the skill's simplicity. | 3 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.