The description names the domain (SEO) and some actions like 'audit, review, or diagnose SEO issues,' but it doesn't list multiple specific concrete actions (e.g., check meta tags, analyze crawl errors, evaluate page speed scores, review internal linking). The actions remain somewhat high-level.

Clearly answers both 'what' (audit, review, diagnose SEO issues) and 'when' with an extensive explicit trigger list. It also includes boundary guidance distinguishing this skill from related skills (programmatic-seo, schema, ai-seo), which strengthens the 'when' component.

Excellent coverage of natural trigger terms users would actually say, including conversational phrases like 'why am I not ranking,' 'my traffic dropped,' 'not showing up in Google,' 'my SEO is bad,' plus technical terms like 'core web vitals,' 'crawl errors,' and 'indexing issues.'

Explicitly differentiates itself from related skills (programmatic-seo, schema, ai-seo) with clear boundary guidance. The focus on auditing/diagnosing SEO issues creates a distinct niche, and the cross-references reduce conflict risk significantly.

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 HTTPS is, basic SEO concepts). Sections like 'Security & HTTPS', 'URL Structure', 'Meta Descriptions', and 'E-E-A-T Signals' are largely restating common SEO knowledge that Claude possesses. The international SEO section alone is massive and could be entirely in a reference file.

The skill provides structured checklists and specific thresholds (e.g., LCP < 2.5s, CLS < 0.1) which are useful, and includes some concrete commands like the JS console query for schema detection. However, it lacks executable code examples, specific curl/fetch commands, or copy-paste-ready scripts for performing audit steps. Most guidance is descriptive ('check for X') rather than showing exactly how to check.

The audit framework establishes a clear priority order (Crawlability → Technical → On-Page → Content → Authority) and the output format section provides good structure. However, there are no explicit validation checkpoints or feedback loops within the audit process itself — no 'if you find X, then do Y before proceeding' patterns. The initial assessment questions are good but the transition from assessment to audit execution is implicit.

The skill references external files (references/international-seo.md, references/ai-writing-detection.md) and related skills, which is good. However, the massive international SEO section is inlined when it should largely live in the referenced file. The on-page SEO, content quality, and common issues sections are all inlined despite being reference-level detail that could be split out. No bundle files were provided to verify references exist.