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 lean, well-structured reference of compact tables plus one bundled audit script, but it functions as a knowledge sheet rather than executable guidance: it lacks implementation templates, a sequenced workflow, and any validation steps.
Suggestions
Add concrete, copy-paste-ready examples for the checklist items (e.g., a sample Article/FAQPage JSON-LD block and a question-based title template) to lift actionability.
Define a short sequenced workflow with a validation checkpoint, e.g. run geo_checker.py -> review citation-readiness gaps -> apply fixes -> re-run, rather than leaving the audit as a bare command.
Move the longer reference tables (RAG factor weights, crawler list) into a references/ file linked from SKILL.md so the overview stays scannable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is almost entirely compact reference tables with little prose padding, and it largely avoids re-explaining concepts Claude already knows; only minor trims are needed (the "What is GEO?" definition and the closing "Remember" line). | 4 / 5 |
Actionability | There is one concrete executable command ("python scripts/geo_checker.py <project_path>") and specific checklist items, but most guidance is high-level advice without templates or code (e.g., "Article schema with dates" with no markup example), leaving key execution details missing. | 3 / 5 |
Workflow Clarity | Sections 1-9 provide a topical order (what -> landscape -> factors -> content -> checklist -> measurement) but no sequenced workflow, and validation/checkpoints are entirely absent even around the audit script. | 2 / 5 |
Progressive Disclosure | Content is well-organized into clearly headed sections, and the one bundled file (scripts/geo_checker.py, confirmed present) is clearly signaled with its command; most reference material is appropriately inline, with only minor opportunity to split detailed tables out. | 4 / 5 |
Total | 13 / 20 Passed |