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 an extremely lean, unambiguous delegation stub: it tells Claude exactly one thing — call the 'moai' skill with the 'feedback' subcommand and the passed arguments — with zero wasted tokens. Its only weakness is that argument semantics and the feedback workflow are entirely undocumented here, leaving a minor actionability gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a single lean line — 'Use Skill("moai") with arguments: feedback $ARGUMENTS' — with no padding, no explanation of concepts Claude already knows, and nothing that could be trimmed. It matches 'Lean and efficient; assumes Claude's competence; every token earns its place'. | 5 / 5 |
Actionability | The body gives one concrete, executable instruction with an exact skill name and subcommand, which is copy-paste-ready guidance. It falls short of a 5 because valid arguments and the expected feedback flow are unspecified — a minor gap left entirely to the delegated 'moai' skill. | 4 / 5 |
Workflow Clarity | This is a simple single-purpose skill whose single action — invoke the 'moai' skill with 'feedback <args>' — is unambiguous, so the simple-skill exception applies and workflow clarity can score 5. Creating a GitHub issue is not a destructive or batch operation, so the validation cap does not apply. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (no references/, scripts/, or assets/ directories exist), and its delegation to Skill("moai") is a single clearly signaled pointer. Per the scoring notes for such simple skills, progressive disclosure scores 5. | 5 / 5 |
Total | 19 / 20 Passed |