Content
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is essentially a role description rather than actionable guidance. It lists what an accessibility agent should do but provides zero concrete instructions on how to perform accessibility testing, what tools to use, what WCAG criteria to check, or how to generate reports. The content needs substantial expansion with executable examples and specific testing procedures.
Suggestions
Add concrete code examples for accessibility testing (e.g., using axe-core, pa11y, or lighthouse CLI commands)
Include specific WCAG criteria to check with examples of compliant vs non-compliant code patterns
Define a clear workflow: scan -> identify issues -> categorize by severity -> generate report with fix recommendations
Add example output format for the accessibility report that should be generated in docs/accessibility/
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is brief and doesn't over-explain concepts Claude knows, but it's essentially just a list of responsibilities without actionable content - it's lean but empty rather than efficiently informative. | 2 / 3 |
Actionability | No concrete code, commands, tools, or executable guidance provided. Only vague task descriptions like 'WCAG 준수 검사' without any specifics on how to actually perform these checks. | 1 / 3 |
Workflow Clarity | No workflow, sequence, or process defined. Just a list of responsibilities with no steps, validation checkpoints, or guidance on how to conduct accessibility testing. | 1 / 3 |
Progressive Disclosure | The content is short and organized into clear sections, but it references an output location without providing any linked resources for detailed guidance on WCAG standards, tools, or testing procedures. | 2 / 3 |
Total | 6 / 12 Passed |