Content
81%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.
A well-structured, actionable review workflow with clear sequencing and an explicit completeness checklist. Main weaknesses are minor redundancy between the lens-priority and trigger sections and total dependence on an external constitution file for the actual lens definitions.
Suggestions
Consolidate the COR/SEC/INC principle IDs so each appears in either the Step 4 lens-priority list or the Step 5 triggers table, not both, to remove redundancy.
Embed at least a one-line definition of each of the 8 lenses inline so the skill remains usable if .opencode/rules/review-constitution.md is missing.
Move the MockServer-Specific Triggers table into a references/ file and link to it, keeping SKILL.md as a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and directive without explaining concepts Claude already knows, but the Lens Priority list (Step 4) and the MockServer triggers table (Step 5) partially duplicate the same COR/SEC principle IDs, a minor trim opportunity. | 4 / 5 |
Actionability | Provides copy-paste git commands, a concrete finding-format template, an output-structure template, and a pattern-to-checks table, but the actual 8-lens definitions are delegated to an external constitution file rather than included, leaving a small gap. | 4 / 5 |
Workflow Clarity | A clear 8-step sequence culminates in an explicit Step 7 validation checklist (verify ALL of these) before the Step 8 verdict, providing explicit checkpoints and a feedback loop for completeness. | 5 / 5 |
Progressive Disclosure | Well-organized into clearly headed steps with a one-level-deep, well-signaled reference to .opencode/rules/review-constitution.md, but no bundle files exist to verify the reference and the MockServer-specific trigger content is inlined rather than split out. | 4 / 5 |
Total | 17 / 20 Passed |