Conciseness

Mostly efficient and densely packed with skill-specific research Claude does not know (ChatGPT 5.6 format-shift numbers, the Princeton GEO table), but Google's 'no special markup / write for people' stance is restated in at least five sections ('Google's Official Stance', the machine-readable files callout, 'What NOT to Do', 'Search Console expectations', and the schema section), and time-sensitive figures ('BrightEdge, Feb 2026', 'Profound, July 2026', 'Ahrefs, Dec 2025') are scattered throughout rather than isolated. This sits at 'mostly efficient but could be tightened' rather than 4 because of that repetition and pervasive dated stats, and not 2 because almost none of it explains concepts Claude already knows.

Actionability

For an instruction-only skill the guidance is fully actionable: a copy-paste-ready /pricing.md template, fill-in audit tables ('Clear definition in first paragraph? | Pass/Fail'), concrete numeric rules ('Keep key answer passages to 40-60 words', 'Run each query 3-5 times per platform and track the mention rate'), named user agents to check, and a runnable command ('npx is-agentic'). Specific examples cover the common cases, matching the top anchor under the rubric's instruction-only scoring note.

Workflow Clarity

A clear sequence is present — 'Before Starting' context gathering, the numbered 'AI Visibility Audit' Steps 1-4, three-pillar optimization, then monitoring ('Check AI visibility monthly at minimum') — and 'Turn findings into work' converts audit findings into fixes. It falls short of 5 because the end-to-end measure → fix → re-measure loop is implied across sections rather than stated once as an explicit checkpointed workflow, and short of the anchor below only in that no destructive or batch operation lacks validation.

Progressive Disclosure

The 'Reference Routing' table maps concrete user questions to all 15 bundled reference files, each verified present in references/ (3.5-16KB, one level deep), with on-demand reading guidance ('read additional references only when their topics are relevant') and explicit fallback behavior if a file is missing ('say which reference is unavailable and use the core workflow'). Detail is appropriately deferred (platform factors, content templates, OKF implementation all live in references), matching the 'clear overview with well-signaled one-level-deep references' anchor.

Specificity

The description names the domain and a couple of concrete outcome-actions — "optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers" — but these are near-synonymous restatements of one capability, and the skill's actual breadth (visibility audits, monitoring, agent readiness, machine-readable files) is not covered, matching 'names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because the coverage gaps are more than minor, and not a 2 because the stated actions are specific rather than generic.

Completeness

Both halves are explicit: what it does ("optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers") and when to use it ("Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines"), plus a long 'use when the user mentions' trigger list. It also adds boundary redirects ('For traditional technical and on-page SEO audits, see seo-audit'), clearly matching the top anchor with concrete trigger phrases.

Trigger Term Quality

Trigger coverage is comprehensive and natural, spanning acronyms and their expansions ("'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization'"), platform-specific phrasings ("'optimize for ChatGPT,' 'optimize for Perplexity,' 'optimize for Claude/Gemini'"), literal user questions ("'how do I show up in AI answers,' 'do listicles still work for AI'"), and file/protocol names ("'llms.txt,' 'llms-full.txt,' 'OKF,' 'WebMCP'"). This matches the anchor for comprehensive natural terms including synonyms; only a few exotic terms could be added.

Distinctiveness Conflict Risk

The skill occupies a clear niche (AI search/AEO) with distinct trigger terms, and explicitly disambiguates from the closest adjacent skills — "For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema." — so mis-triggering risk against generic SEO skills is minimal, matching the 'clear niche with distinct triggers' anchor.