Content
92%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 concise, highly actionable, well-sequenced workflow with strong guardrails — the main weakness is that everything lives in one file with no progressive disclosure via reference files.
Suggestions
Move the per-tool API detail (the 'OpenSEO MCP tools' section) into a references file and link to it, keeping SKILL.md as a concise overview.
Consider a separate references doc for the output-format/table guidance so the workflow stays lean.
Add clearly signaled, one-level-deep reference links (e.g. See TOOLS.md) to lift progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient throughout; assumes Claude's competence, never explains what Maps/GBP is, and every line carries actionable information. | 5 / 5 |
Actionability | Fully executable guidance — concrete tool names, specific parameters (minRating, isClaimed: false, 3x3 vs 5x5), exact thresholds (>5 locations → ask), and cid/place_id matching rules. | 5 / 5 |
Workflow Clarity | An 8-step sequenced workflow with explicit validation checkpoints for paid/batch operations (check research log before spending credits, confirm coordinate before grid) and a prioritization rule. | 5 / 5 |
Progressive Disclosure | Well-organized into sections, but with no bundle files all content is inline in a single SKILL.md rather than split into one-level-deep references. | 3 / 5 |
Total | 18 / 20 Passed |