Content
28%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a general knowledge dump about E-E-A-T concepts than an actionable guide for Claude. It extensively lists things Claude already knows (what trust signals are, what author bios are) without providing concrete implementation details, specific code/markup examples, or a rigorous audit methodology. The referenced implementation playbook doesn't exist in the bundle, leaving the skill without the depth it promises.
Suggestions
Replace the verbose E-E-A-T framework lists with a concise scoring rubric that has specific, measurable criteria (e.g., 'Author bio present with 2+ credentials: +2 points') rather than generic category lists.
Add concrete, executable examples: include actual schema markup JSON-LD snippets for Organization/Person schema, a real author bio template with placeholder fields, and a sample audit output with specific findings.
Define a clear workflow with validation: specify how to score current content (with measurable criteria), set a threshold for 'passing', and include a verification step to confirm improvements were implemented correctly.
Either provide the referenced 'resources/implementation-playbook.md' bundle file or remove the reference and inline the essential implementation details directly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is noticeably verbose with extensive lists of concepts Claude already understands (what E-E-A-T stands for, what SSL certificates are, what privacy policies are). The focus areas, framework breakdown, and multiple bulleted lists of obvious items significantly pad the content without adding actionable value. | 2 / 5 |
Actionability | The skill provides high-level checklists and lists of things to consider but lacks any concrete, executable guidance. There are no specific code examples, no actual schema markup snippets, no real audit methodology, and no concrete steps for implementation. The output template is a vague placeholder ('X/10', '[subject]') rather than a worked example. | 2 / 5 |
Workflow Clarity | The 'Approach' section lists 7 steps but they are vaguely defined ('Analyze content for existing E-E-A-T signals') with no validation checkpoints, no feedback loops, and no clear criteria for how to assess or score signals. The workflow is more of a rough outline than a clear sequence. | 2 / 5 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, which is good progressive disclosure practice. However, no bundle files exist to support this reference, and the bulk of the content (framework details, tactics, platform implementation) is inlined when much of it could be split into separate reference files. The structure has sections but they're all at the same level of detail. | 3 / 5 |
Total | 9 / 20 Passed |