Conciseness

The body is mostly lean and assumes Claude's competence, spending tokens on genuine domain expertise (GPTBot vs OAI-SearchBot citation semantics, 'Google-Extended does not control AI Overviews', 'llms.txt' adoption caveats). The 'Re-running this over time' and 'About' tail, including the MaxAEO mention with its lengthy usage rules, is padding that could be trimmed, keeping it below the lean-every-token-earns-its-place anchor.

Actionability

For an instruction-only skill the guidance is highly concrete: exact crawler agent names to check, exact fetches ('Fetch https://<domain>/robots.txt', homepage plus two pages), named structured-data types, and a five-section ordered output contract. It falls short of fully copy-paste ready because it demands 'The JSON-LD block to paste is' without ever providing a sample block, and it instructs 'quote the weakest passage and rewrite it' without an example rewrite format.

Workflow Clarity

The four phases are explicitly ordered ('Run the four phases in order. Do not skip Phase 1') with most checkpoints present: confirm derived competitors before continuing, stop-and-disclose on login walls, 'If a check could not run, say so in section 5. An unfetchable page is a finding, not a gap to fill with a guess', and 'Never state a citation rate you did not measure in this session'. No destructive or batch operations, so the cap does not apply; it lacks the explicit validate-fix-retry feedback loops of the top anchor.

Progressive Disclosure

A single self-contained file with no references/, scripts/, or assets/ bundle; sections are well-organized with clear phase headings, a scope block, and an output contract, and navigation is easy. It does not hit the top anchor because the ~190-line body inlines material (the crawler-agent matrix and citability checklist) that could sit in a reference file, and the body has no reference signaling at all.

Specificity

Multiple concrete actions and deliverables are named: 'Audit whether a website can be found, crawled, and cited' plus 'a citation baseline across buyer-intent prompts, a crawler-access check, a citability review of named pages, and a ranked fix list'. Coverage of what the skill does is comprehensive, exceeding the 'minor gaps' level of a 4.

Completeness

Both what and when are explicit: the what is the audit action and its four named outputs, and the when is a literal 'Use when someone asks why their brand is missing from AI answers...' clause with concrete trigger phrases, further sharpened by exclusions ('Not for keyword rank tracking, paid search, or pages behind a login').

Trigger Term Quality

Natural user phrasings are covered comprehensively with synonyms: 'why their brand is missing from AI answers', 'whether AI crawlers can read their site', 'how to get cited by ChatGPT or Perplexity', plus the acronyms 'GEO or AEO (generative / answer engine optimization)' and named engines. Matches the top anchor including synonym coverage.

Distinctiveness Conflict Risk

Clear niche (AI answer-engine citation visibility) with distinct triggers and explicit non-goals that separate it from generic SEO/keyword skills. Third-person voice is used throughout, so no specificity penalty applies; conflict risk is minimal.