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 functions more as a comprehensive SEO audit reference manual than a concise, actionable skill file. Its greatest strength is the schema markup detection limitation warning and the international SEO detail, which contain genuinely non-obvious information. However, the vast majority of content covers standard SEO knowledge that Claude already possesses, making it extremely token-inefficient. The checklist format provides structure but lacks executable commands, validation steps, and decision-tree logic that would make it truly actionable.
Suggestions
Reduce the body to ~100 lines focusing on: (1) the initial assessment workflow, (2) audit priority order with brief descriptions, (3) non-obvious gotchas like schema detection limitations, and (4) the output format. Move all detailed checklists (technical SEO, on-page, content quality, site-type issues) into reference files.
Add concrete executable examples — e.g., specific curl commands to check robots.txt, sitemap validation commands, or code snippets to parse Search Console data — rather than abstract checklists like 'check for unintentional blocks'.
Add validation checkpoints and decision logic to the workflow: e.g., 'After crawlability check, if >10% of pages are not indexed, STOP and prioritize indexation fixes before proceeding to on-page audit.'
Remove sections that explain concepts Claude already knows well (E-E-A-T definitions, what title tags are, what HTTPS is, what alt text is) and replace with only the non-obvious checks and common mistakes specific to each area.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, with extensive checklist-style content that Claude already knows (what title tags are, what meta descriptions are, what E-E-A-T stands for, basic HTTPS concepts). Sections like 'Security & HTTPS', 'URL Structure', 'Mobile-Friendliness', and 'Content Quality Assessment' explain fundamental SEO concepts that add little value for an AI that already understands them. The international SEO section alone is massive and could be entirely in a reference file. | 1 / 3 |
Actionability | The skill provides structured checklists and specific thresholds (e.g., LCP < 2.5s, CLS < 0.1) which are useful, and the schema markup detection limitation is a genuinely actionable insight. However, there are no executable code examples, no specific commands to run, and most guidance is checklist-style ('check for X') rather than concrete steps with tool invocations. The audit is more of a reference document than executable instructions. | 2 / 3 |
Workflow Clarity | The priority order (Crawlability → Technical → On-Page → Content → Authority) provides a clear sequence, and the output format section gives good structure for deliverables. However, there are no validation checkpoints, no feedback loops for when issues are found, and no explicit decision points (e.g., 'if X then do Y, otherwise skip'). The initial assessment section is well-structured but the audit itself reads as a flat checklist rather than a guided workflow. | 2 / 3 |
Progressive Disclosure | The skill references external files (references/international-seo.md, references/ai-writing-detection.md) and related skills appropriately, but the main body contains enormous amounts of detail that should be in reference files — particularly the full international SEO section, the complete on-page audit checklists, and the site-type-specific issues. The content that IS inline is far too much for a SKILL.md overview. No bundle files were provided to verify references exist. | 2 / 3 |
Total | 7 / 12 Passed |