Content
100%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.
An exemplary instruction-only skill body: lean, concrete, and precisely scoped, with numeric confidence thresholds and a sharp exclusion list that keeps the reviewer on-task. The only substantive gap sits in the frontmatter description, not the content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — terse sections ('What you're hunting for', 'Confidence calibration', 'What you don't flag') with no padding and no explanation of concepts Claude already knows. Every token earns its place. | 5 / 5 |
Actionability | Concrete, executable guidance throughout: numeric confidence thresholds ('HIGH (0.80+)', 'MODERATE (0.60-0.79)', 'Below 0.50: Suppress entirely'), an explicit instruction ('Flag with `autofix_class: auto` and group by logical theme, keeping original R# IDs'), and testable criteria ('The test is whether a reader could be confused'). For an instruction-only skill this is copy-paste-ready direction. | 5 / 5 |
Workflow Clarity | A single-purpose skill with an unambiguous action sequence: hunt for the listed finding types, calibrate confidence, suppress below 0.50, and apply the explicit exclusion list. Per the simple-skill guideline this can score 5, and no destructive or batch operations exist to require validation checkpoints. | 5 / 5 |
Progressive Disclosure | At under 50 lines with no need for external references, the well-organized sections (hunt / calibrate / exclusions) fully satisfy progressive disclosure; no bundle files exist and none are needed. | 5 / 5 |
Total | 20 / 20 Passed |