Content
67%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable reference for AI-search optimization with a clear audit workflow and verified external references. Its main weaknesses are length/padding, time-sensitive statistics that will date, and a large inlined body that could push more detail into reference files.
Suggestions
Move time-sensitive statistics (the 45%/58%/6.5x/3x figures and the Princeton GEO boost table) into references/ or a dated 'Current data' section so the main body stays evergreen.
Trim the 'You are an expert in AI search optimization...' role preamble and other explanatory prose to tighten the token budget.
Externalize the schema-markup catalog and monitoring-tools tables into a reference file to reduce inlined bulk and deepen progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly information-dense via tables, but the ~400-line body carries padding (the "You are an expert in AI search optimization" role preamble) and time-sensitive statistics ("AI Overviews appear in ~45% of Google searches", "6.5x more likely") that will date and are not isolated in a deprecated/old-patterns section, matching 'mostly efficient but includes some unnecessary explanation'. | 3 / 5 |
Actionability | Concrete and specific for an instruction skill — named content block patterns, schema types (Article/HowTo/FAQPage/Product), structural rules ("40-60 words", "Lead every section with a direct answer"), named bots (GPTBot, PerplexityBot), and named monitoring tools — with only minor abstract bits like "Improve readability and flow". | 4 / 5 |
Workflow Clarity | The AI Visibility Audit is a clearly sequenced 4-step process whose Step 3 includes a Pass/Fail extractability checklist acting as a validation checkpoint, but there is no explicit fix-and-re-check feedback loop, matching 'clear sequence with most checkpoints present; minor validation gaps'. The destructive/batch cap does not apply since this is advisory content. | 4 / 5 |
Progressive Disclosure | SKILL.md acts as an overview with two real, well-signaled, one-level-deep references (references/platform-ranking-factors.md and references/content-patterns.md, both verified present), but a body this large keeps dense tabular material (Princeton GEO methods, schema catalog, monitoring tools, content-type shares) inlined that could be split out, matching 'good structure; most content appropriately placed; minor organization gaps'. | 4 / 5 |
Total | 15 / 20 Passed |