Content
93%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 routing skill body: lean, executable, and well-structured with a validated dispatch gate and one-level-deep references. The only minor gap is the absence of an in-body error-recovery feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | A lean ~30-line dispatcher that assumes Claude's competence and avoids explaining known concepts; every line is actionable instruction with no padding. | 5 / 5 |
Actionability | Provides a copy-paste-ready command ('node <skill-dir>/scripts/cli.mjs init --status') and concrete routing conditions with explicit per-action reference files. | 5 / 5 |
Workflow Clarity | A clear numbered sequence with an explicit init-gate validation checkpoint and stop conditions, though the body itself routes rather than embedding a fix-retry feedback loop. | 4 / 5 |
Progressive Disclosure | SKILL.md is a clean overview that dispatches to nine one-level-deep action reference files plus help/commands docs, with clearly signaled navigation and no nested doc-chasing. | 5 / 5 |
Total | 19 / 20 Passed |