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 a well-structured, executable, concise skill that tells Claude exactly what to run and how to handle failures. The only minor weakness is light redundancy between the invocation and sandbox sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence — concrete commands with no concept padding — but the 'Explicit invocation only' and 'Sandbox access' sections lightly restate the trigger gate and could be trimmed slightly. | 4 / 5 |
Actionability | It gives copy-paste-ready commands covering the common cases ('roborev snooze on', 'roborev snooze on --duration 2h', 'roborev snooze off') with explicit flag handling. | 5 / 5 |
Workflow Clarity | This is a simple single-action skill with unambiguous on/off branches and explicit error-reporting guidance for both sandbox permission failures and non-git directories; no destructive/batch cap applies. | 5 / 5 |
Progressive Disclosure | Under 50 lines, no external references needed, and organized into clearly labeled sections (Usage, Explicit invocation only, Sandbox access, Instructions, Examples), satisfying the simple-skill exception. | 5 / 5 |
Total | 19 / 20 Passed |