Conciseness

The same instructions appear three times: the 'Check' section ('Search the site for all instances of the business name, street address, and phone number... check JSON-LD LocalBusiness schema against the visible text') is nearly verbatim duplicated in 'Code Review' ('Extract all instances of the business name, street address, and phone number... compare against visible HTML text'), and the 'Quick Reference' bullets repeat both a third time. The 'Explain' section also teaches a concept Claude already knows ('NAP consistency is a local SEO ranking factor. Google cross-references...'). This matches anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections') — above 1 because each section is individually terse and on-topic, but below 3 because the duplication and the concept explanation are clear padding that could be cut to roughly a third of the body.

Actionability

For an instruction-only skill the guidance is concrete: exact comparison targets ('St.' vs 'Street', '555-1234' vs '(555) 123-4567', suite notation), a clear canonical-format decision process in 'Fix' ('Choose one format for each field: full street name vs abbreviation, phone number formatting, suite/unit notation'), and named locations to check (footer, contact page, about page, structured data). This matches anchor 4 ('mostly executable guidance... with minor gaps') — below 5 because there are no commands or report format (e.g., a site-wide search command or the output format for 'Report any differences'), and the body defers all code examples to references/rule.md; above 3 because the guidance is specific and directly executable, not pseudocode.

Workflow Clarity

A rough sequence exists (Check → Fix → Explain), but the near-duplicate 'Check' and 'Code Review' sections muddy which procedure to follow and in what order, and there is no validation checkpoint after the batch 'Fix' step ('Update all pages, footer, contact page, about page, and structured data') — nothing says to re-run the comparison to confirm zero remaining inconsistencies. This matches anchor 3 ('steps listed but validation gaps') and the rubric's cap for batch operations without a feedback loop; below 4 because a multi-page batch edit with no re-verify step is a missing checkpoint, above 2 because the audit-then-fix order is coherent and the check itself is well defined.

Progressive Disclosure

The body is a clear, well-organized overview (Quick Reference / Check / Fix / Explain / Code Review) with a single, clearly signaled, one-level-deep reference: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md' — and references/rule.md exists and delivers exactly that (inconsistency patterns table, where-to-check list, HTML/JSON-LD examples, verification steps). No nested references exist. This matches anchor 5 ('clear overview with well-signaled one-level-deep references') — the body keeps examples inline and pushes depth to the reference file appropriately.

Specificity

The description names the domain ('auditing a local business website for local SEO') and one concrete action (auditing), but never states what the audit actually covers — NAP (Name, Address, Phone) consistency is entirely absent, so it reads as a single generic action rather than several specific ones. Anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') fits best; it is above anchor 2 because the domain is specific, and below anchor 4 because no specific capability beyond 'auditing' is listed.

Completeness

Both elements are present: the 'what' is 'auditing a local business website for local SEO' and the 'when' is explicit ('Use when auditing...'; 'Applies to any business that has a physical address and wants to appear in local search results or Google Maps'). It is not a 5 because the 'what' is underspecified — the description never says what the audit checks (NAP consistency) — leaving the core capability implicit; it is above 3 because the 'Use when' trigger is explicit and concrete rather than weakly implied.

Trigger Term Quality

Natural phrases users would say are present: 'local SEO', 'local search results', 'Google Maps', 'physical address', 'local business website'. However, common synonyms a user might actually say are missing: 'NAP', 'Google Business Profile', 'local listings', 'business name/address/phone'. This matches anchor 4 ('good keyword coverage; a few natural terms missing') — above 3 because coverage is solid and multi-word natural, below 5 because the core term the skill is about (NAP) and related synonyms are absent.

Distinctiveness Conflict Risk

The niche is fairly distinct — local SEO auditing of businesses with physical addresses — and unlikely to trigger for unrelated skills. Minor overlap risk remains with closely related SEO skills (e.g., LocalBusiness structured-data markup or general site SEO audits), which could also match phrases like 'local SEO' or 'business website'. This matches anchor 4 ('mostly distinct; minor overlap risk with closely related skills') — below 5 because 'local SEO' is a trigger shared by sibling SEO skills, above 3 because the physical-address/local-search framing is quite specific.