Content
96%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 an exceptionally lean, actionable instruction skill with concrete MCP tool/parameter guidance, a well-sequenced workflow, and explicit cost- and coordinate-validation checkpoints; its only soft spot is progressive disclosure, where a self-contained structure with no reference files leaves minor organization headroom.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and instruction-dense: it assumes Claude knows SEO and never explains what a Google Business Profile or local pack is, with every section (tools, workflow, guardrails) earning its place; not the 4 anchor because there is no over-explanation to trim. | 5 / 5 |
Actionability | Gives concrete, executable guidance — specific MCP tools with exact parameters (isClaimed, minRating, cid/place_id, 3x3 vs 5x5 grids) and precise thresholds (30-day reuse, '5 locations or fewer', '30-60 seconds' retry); absence of code is not penalized for an instruction-only skill per scoring notes. | 5 / 5 |
Workflow Clarity | An explicit 8-step sequence with validation checkpoints (reuse the research log if <30 days, confirm the coordinate matches the storefront before spending credits, warn about 5x5 grid cost), a reviews processing→taskId→retry feedback loop, and a multi-location decision checklist; meets the 'explicit validation steps; feedback loops; checklists' anchor. | 5 / 5 |
Progressive Disclosure | Well-organized into clear sections (Goal, Required inputs, Project context, MCP tools, Workflow, Output format, Guardrails) with no bundle files to split; sits at the 'good structure, content appropriately placed, minor gaps' anchor rather than 5 because the inline ~9-tool reference list and the absence of one-level-deep references leave minor organization room. | 4 / 5 |
Total | 19 / 20 Passed |