accessibility-compliance-accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, identify barriers, and provide remediation guidance.
Install with Tessl CLI
npx tessl i github:duclm1x1/Dive-Ai --skill accessibility-compliance-accessibility-audit56
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 establishes a clear accessibility domain and mentions relevant technical concepts, but suffers from using second person voice ('You are') which violates the third-person requirement. It lacks explicit trigger guidance ('Use when...') and misses common user terminology variations. The actions listed are somewhat generic rather than concrete specific capabilities.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user asks about accessibility, WCAG compliance, screen reader support, color contrast, keyboard navigation, or ADA requirements'
Rewrite in third person voice: 'Conducts accessibility audits, identifies WCAG compliance issues, and provides remediation guidance for inclusive design'
Include common user terminology variations: 'a11y', 'screen reader', 'alt text', 'color contrast', 'keyboard accessible', 'ADA'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (accessibility/WCAG) and some actions ('conduct audits, identify barriers, provide remediation guidance'), but these are somewhat general rather than listing multiple concrete specific actions like 'test screen reader compatibility, validate color contrast ratios, check keyboard navigation'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no 'when' component at all. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'WCAG', 'accessibility', 'inclusive design', 'assistive technology', but misses common user variations like 'a11y', 'screen reader', 'ADA compliance', 'color contrast', 'keyboard navigation', or 'alt text'. | 2 / 3 |
Distinctiveness Conflict Risk | The accessibility/WCAG focus provides some distinctiveness, but 'conduct audits' and 'provide guidance' are generic enough to potentially overlap with other audit or compliance-related skills. The domain is clear but triggers are not sharply defined. | 2 / 3 |
Total | 7 / 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 provides a reasonable high-level framework for accessibility auditing with good progressive disclosure to detailed resources. However, it lacks concrete actionability - no specific tool commands, code examples, or validation checkpoints that would make it immediately executable. The content is moderately concise but has some redundancy between sections.
Suggestions
Add specific tool examples in Instructions (e.g., 'Run axe-core: `npx axe-cli https://example.com`' or 'Use Lighthouse accessibility audit')
Include explicit validation checkpoints, such as 'Verify all critical violations are resolved before proceeding to manual testing'
Remove redundant content between the header description, Context section, and 'Use this skill when' to improve conciseness
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the description in the header repeats the persona context, and the 'Context' section largely restates information from 'Use this skill when'. Could be tightened. | 2 / 3 |
Actionability | Instructions provide a clear sequence of steps but lack concrete examples, specific tool commands, or executable code. 'Run automated scans' and 'Perform manual checks' are directional but not copy-paste actionable without the referenced playbook. | 2 / 3 |
Workflow Clarity | Steps are listed in logical sequence (scope → scan → manual → map → remediate → re-test), but lacks explicit validation checkpoints or feedback loops. No guidance on what to do if automated scans fail or how to verify remediation success before proceeding. | 2 / 3 |
Progressive Disclosure | Clean structure with overview content in SKILL.md and clear one-level-deep reference to implementation-playbook.md for detailed procedures. Well-signaled navigation to the resource file. | 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.
- 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.