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 tight, fully executable instruction sheet: exact commands, explicit error handling, and clear scope boundaries (what snooze must not touch). The only slack is mild redundancy between the invocation-policy section, the frontmatter, and the Examples block. No external references are needed at this size, and structure is clean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes competence, but the 'Explicit invocation only' section largely restates the frontmatter description, and the Examples block repeats commands already fully specified in Instructions. This matches anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') rather than 5, where every token would earn its place. | 4 / 5 |
Actionability | Every variant is given as an exact, copy-paste-ready command with precise flags ('roborev agent hook snooze --from-skill on --duration 2h'), covering the common on/off/duration cases. This matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases'). | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill whose action is unambiguous, and the conditionals (on/off, optional duration) plus error-recovery paths (retry with sandbox_permissions on permission denied; report non-git-repo errors without attempting registration) are explicitly handled. The simple-skill exception applies and the operation is neither destructive nor batch, so 5 is warranted. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references, and is organized into clear, well-labeled sections (Usage, Explicit invocation only, Sandbox access, Instructions, Examples). Per the rubric guideline, this earns a 5 with just well-organized sections. | 5 / 5 |
Total | 19 / 20 Passed |