Conciseness

The body is lean and dense with constraints Claude does not already know: 'Unique <title> (50–60 chars)', 'OG image 1200×630 px', 'sitemap index above 50,000 URLs or 50 MB'. Every line is a concrete rule, threshold, or command — no padding, no explanation of what SEO is, every token earns its place.

Actionability

Guidance is fully executable: exact character budgets, pixel dimensions, a copy-paste extraction command ('curl -s https://example.com/page | pup ... | jq .'), exact Disallow paths, and a concrete robots.txt directive ('Sitemap: https://example.com/sitemap.xml'). Anchor 5 fits — commands are copy-paste ready and cover the common cases.

Workflow Clarity

There are real checkpoints — JSON-LD 'must return 0 errors ... before shipping' and a post-deploy step ('check Search Console for warnings; remove any accidental Disallow: entry and resubmit the sitemap') — but the sequences are implicit rather than ordered, and no explicit fix-and-revalidate loop is spelled out. Anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') fits better than 5, which demands explicit feedback loops and checklists.

Progressive Disclosure

The skill is under 50 lines, self-contained with no bundle files, and cleanly sectioned (Constraints, Structured Data, Sitemap & robots.txt). Per the simple-skill guideline, well-organized sections with no need for external references score 5.

Specificity

It enumerates six concrete, technical items — 'meta tags, Open Graph, canonical URLs, JSON-LD structured data, sitemaps and robots.txt' — with comprehensive domain coverage, but they are named artifacts rather than the concrete action verbs ('extract', 'fill', 'merge') that anchor 5 exemplifies. Anchor 4 ('several specific items; minor gaps') is the closest fit, and anchor 3 (only 1–2 items) is clearly too low.

Completeness

Both halves are explicit: the what ('Technical SEO: meta tags, Open Graph, canonical URLs, JSON-LD structured data, sitemaps and robots.txt') and the when ('Use when adding or fixing any of these, or when pages are not being crawled or indexed'). This matches the anchor-5 good example structurally — a concrete capability list followed by an explicit 'Use when' clause with trigger phrases.

Trigger Term Quality

Natural user phrasings are well covered — 'meta tags', 'canonical URLs', 'sitemap', 'robots.txt', 'not being crawled or indexed' — matching how users actually request technical SEO help. It falls short of anchor 5's comprehensive synonym coverage (e.g., no 'rich results', 'OG tags', 'search snippets'), so anchor 4 ('good keyword coverage; a few natural terms missing') fits best.

Distinctiveness Conflict Risk

'Technical SEO' is a clear niche with distinct, non-overlapping triggers (structured data, sitemaps, canonicals, crawl/indexing) — minimal conflict risk with any adjacent web-dev skill. Anchor 5 is the direct match; anchor 4's 'minor overlap risk with closely related skills' does not apply since the triggers are unambiguous.