Content
43%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 well-structured reference material with a useful checklist and an audit script, but it lacks a sequenced workflow and inlines content that could live in reference files. It reads more as a cheat-sheet than an actionable procedure.
Suggestions
Convert the numbered sections into an explicit sequenced workflow (audit -> optimize content -> add schema -> verify crawler access -> measure) with validation checkpoints.
Move the large reference tables (RAG retrieval factors, engine landscape) into a references/ file and keep SKILL.md as a concise overview with one-level-deep links.
Add a short executable example for the checklist (e.g. a JSON-LD FAQPage schema snippet) to lift actionability beyond descriptive guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The dense table format is mostly efficient, but 'What is GEO' and 'SEO vs GEO' sections explain basics Claude largely already knows and could be trimmed. | 3 / 5 |
Actionability | The checklist provides concrete items (e.g. 'Article schema with dates', 'Question-based titles') and one script command, but the bulk is descriptive reference material with no code examples. | 3 / 5 |
Workflow Clarity | Sections are numbered 1-9 but there is no sequenced workflow or validation checkpoints; it reads as topical reference rather than a guided process. | 2 / 5 |
Progressive Disclosure | Sections are clearly organized and the script reference (scripts/geo_checker.py, a real file) is properly signaled, but substantial reference content (RAG factors, engine landscape) is inlined rather than split into separate files. | 3 / 5 |
Total | 11 / 20 Passed |