Content
55%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.
The body is a well-structured, fairly actionable reference with a real bundled audit script, but it reads as topical reference material rather than a sequenced workflow and includes some concept re-explanation Claude does not need.
Suggestions
Replace the conceptual 'What is GEO' / 'SEO vs GEO' sections with a one-line definition and keep only operational guidance.
Add a short numbered workflow around the checker: run geo_checker.py → review flagged gaps → apply fixes → re-run to confirm.
Include a minimal example robots.txt snippet and one FAQPage schema JSON block so the checklist items are copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly compact tables, but sections like 'What is GEO' and 'SEO vs GEO' re-explain concepts Claude already knows, and the closing 'Remember' blockquote is padding. | 3 / 5 |
Actionability | It supplies a runnable command (python scripts/geo_checker.py <project_path>), concrete schema types (Article/Person/FAQPage), named AI crawler user-agents, and checklists; as an instruction-only skill the lack of code snippets is not heavily penalized, though example robots.txt/schema JSON would close the gap. | 4 / 5 |
Workflow Clarity | Content is organized as topical reference sections (1–9), not a sequenced process; there is no audit→fix→re-audit loop or validation checkpoint around the checker script. | 2 / 5 |
Progressive Disclosure | Sections are well organized and the single bundle reference (scripts/geo_checker.py, which exists) is clearly signaled at one level of depth; minor gap is that conceptual reference tables are inlined rather than split out. | 4 / 5 |
Total | 13 / 20 Passed |