Content
56%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-structured with a clear sequenced workflow and explicit re-test feedback loop, but it is held back by redundant restating of the description, high-level actionability, and a referenced playbook file that is missing from the bundle.
Suggestions
Remove or condense the opening persona paragraph and Context section, which duplicate the frontmatter description.
Name specific tools in the instructions (e.g. axe-core/Lighthouse for automated scans, NVDA/VoiceOver for screen-reader checks) to make guidance executable.
Provide the referenced 'resources/implementation-playbook.md' bundle file, or drop the reference if no detailed material exists.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient, but the opening persona paragraph nearly duplicates the frontmatter description and the Context section restates the same purpose, which is padding that could be trimmed. | 3 / 5 |
Actionability | The instructions give concrete categories (keyboard, screen reader, focus order, contrast; platforms, WCAG level) but stay high-level, omitting specific tool names (e.g. axe-core, Lighthouse, NVDA) and concrete steps. | 3 / 5 |
Workflow Clarity | The six steps are clearly sequenced from scoping through remediation to 're-test after fixes', providing an explicit validation checkpoint with only minor gaps. | 4 / 5 |
Progressive Disclosure | Structure and signaling are good with a one-level-deep reference to 'resources/implementation-playbook.md', but no bundle directory (resources/) or file actually exists, so the reference is a dangling pointer. | 3 / 5 |
Total | 13 / 20 Passed |