Conciseness

The ~30-line body is lean: bullets like "Place `<meta name="robots" content="...">` in `<head>`" and "Crawler-specific tags (`googlebot`, `bingbot`) override the generic `robots` tag" convey only non-obvious guidance with no padding and no explanation of concepts Claude already knows. Every section earns its place; matches 'lean and efficient; every token earns its place'.

Actionability

The guidance is concrete and executable — "Inspect `<head>` for `<meta name="robots" content="...">`", "production pages should not have `noindex`", "Check for conflicting `googlebot`-specific tags", "Remove duplicate or conflicting robots meta tags" — with exact tag syntax throughout. Per the rubric's instruction-skill note, absent code is not penalized, but there are no copy-paste commands or rendered-output examples in the body itself (they live in references/rule.md), so it fits 'mostly executable guidance; concrete code or commands with minor gaps' rather than 5.

Workflow Clarity

The Check → Fix → Explain → Code Review sections form a coherent audit sequence, and verification is addressed ("describe how to verify the final page output"; the Fix section distinguishes intentional vs. accidental noindex). Matches 'clear sequence with most checkpoints present; minor validation gaps'; not 5, because there is no explicit post-fix validation checkpoint (e.g. re-check rendered HTML or Search Console after removing a noindex); not 3, because the checkpoints are present, just implicit rather than looped.

Progressive Disclosure

The body is a concise overview with well-labeled sections and a single, clearly signaled, one-level-deep pointer — "For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`" — and that file exists in the bundle. This matches the rubric's simple-skill pattern of 'clear overview with well-signaled one-level-deep references'.

Specificity

The description names the domain ("all HTML pages", "meta tag parity") and includes two concrete trigger actions — "auditing pages that have disappeared from search results" and "checking staging vs. production meta tag parity" — but never states the core capability (setting/fixing robots meta directives). It matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than 2, because the actions given are specific rather than generic; not 4, because the primary capability is entirely unstated.

Completeness

Only the 'when' is present ("Use when auditing pages... or when checking staging vs. production meta tag parity") with no 'what' — the description never says what the skill does. This exactly matches the anchor 'only when is present without what'; not 3, because the anchor at 3 requires a clear 'what' with a weak 'when', the inverse of this description's gap.

Trigger Term Quality

"pages that have disappeared from search results" and "staging vs. production" are natural user phrases, but the most common trigger vocabulary is missing: "robots meta", "noindex", "indexing", "SEO", "deindexed", "not showing in Google". This matches 'some relevant keywords but missing common variations or synonyms'; not 4, because several of the most likely user terms are absent.

Distinctiveness Conflict Risk

The triggers are moderately specific to robots-meta auditing ("disappeared from search results", "meta tag parity") but omit 'robots'/'noindex', so adjacent SEO skills (canonical tags, sitemaps, general meta-tag parity checks) could plausibly trigger it. Matches 'somewhat specific but could still overlap with similar skills'; not 4, because the missing niche vocabulary leaves real overlap risk with sibling SEO rules.