Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a comprehensive SEO reference guide rather than a concise, actionable skill for Claude. Its main weakness is extreme verbosity—it explains many concepts Claude already knows (meta descriptions, HTTPS, alt text, Core Web Vitals thresholds) without adding novel insight. The structured output format and priority ordering are strengths, but the lack of concrete examples, executable commands, and validation checkpoints limit its practical utility.
Suggestions
Cut the content by 60-70%: remove explanations of concepts Claude already knows (what meta descriptions are, what HTTPS is, E-E-A-T definitions) and focus only on the specific audit workflow, decision criteria, and output format.
Add a concrete example of audit output—show a sample finding with Issue/Impact/Evidence/Fix filled in so Claude knows exactly what format to produce.
Move the detailed checklists (Technical SEO, On-Page SEO, Content Quality, Site Type issues) into separate reference files and link to them from the main SKILL.md to improve progressive disclosure.
Add validation/verification steps to the workflow—e.g., after identifying issues, verify findings against Search Console data before reporting, or cross-check indexation issues with a site: search.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, largely consisting of checklist items that Claude already knows (what meta descriptions are, what HTTPS is, what alt text is, what Core Web Vitals thresholds are). Most of this is general SEO knowledge that doesn't need to be spelled out. The 'Common Issues by Site Type' and 'E-E-A-T Signals' sections explain well-known concepts rather than providing novel, actionable instructions. | 1 / 3 |
Actionability | The skill provides structured checklists and a clear output format, which gives some concrete guidance on what to check and how to report findings. However, there are no executable code snippets, no specific commands to run, and no concrete examples of audit output—it reads more like a reference document than step-by-step executable instructions. | 2 / 3 |
Workflow Clarity | There is a clear priority order (crawlability → technical → on-page → content → authority) and a structured output format, which provides reasonable sequencing. However, there are no validation checkpoints, no feedback loops for verifying fixes, and no explicit decision points for when to stop or escalate—it's a checklist without a process. | 2 / 3 |
Progressive Disclosure | The skill references two supporting files (ai-writing-detection.md, aeo-geo-patterns.md) and links to related skills, which is good. However, the massive amount of inline content (all the checklists for technical SEO, on-page SEO, content quality, site-type issues) should be split into separate reference files rather than being inlined in the main SKILL.md, making it a monolithic document. | 2 / 3 |
Total | 7 / 12 Passed |