Content
71%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-organized and richly actionable for inline guidance, but it is structured as an overview that defers substantial detail to references and scripts that are missing from the bundle, breaking navigation and leaving three modes dependent on non-existent scripts.
Suggestions
Ship the referenced bundle files — add references/review-response-templates.md, references/local-schema-types.md, references/local-seo-checklist.md, and the three scripts/*.py files the body depends on, so the deferred detail and commands actually resolve.
For the NAP, service-area, and schema workflows, add an explicit validate-then-fix feedback loop (e.g., re-run nap_checker.py after corrections and confirm the mismatch count drops to zero) to satisfy the batch-operation validation expectation.
Trim the framing exposition (e.g., 'Local SEO is a different game from national SEO...') and inline the highest-value deferred content (at least the review-response and schema examples) so the skill remains usable even if a referenced file is absent.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and actionable (checklists, tables, a full page template, specific thresholds like 'LCP < 2.5s' and '750 char max') with little padding, though framing lines such as 'Local SEO is a different game from national SEO' are mild over-explanation that could be trimmed. | 4 / 5 |
Actionability | Concrete, copy-paste-ready guidance abounds — the service area page template, GBP audit checklist, and NAP/schema tables are executable — but three of four modes route through scripts (nap_checker.py, service_area_generator.py, schema_generator.py) that are not present in the bundle, leaving those commands non-executable. | 4 / 5 |
Workflow Clarity | The four modes are clearly sequenced with checklists and a 'Before publishing, verify' uniqueness checkpoint for the batch page-generation workflow, but there is no explicit validate-fix-retry feedback loop around the script-driven batch operations, leaving a minor validation gap. | 4 / 5 |
Progressive Disclosure | Structure is well-intended with clearly signaled one-level-deep references, but the referenced bundle files (references/*.md and scripts/*.py) do not exist, so navigation leads to dead links and deferred detail (full templates, schema examples, the 80-point checklist) is unavailable. | 3 / 5 |
Total | 15 / 20 Passed |