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.
The content is an exemplar of lean, executable skill writing: a five-command diagnostic sequence with an explicit verification step, followed by a concrete prioritized checklist of failure causes. The only meaningful improvement would be making the recovery loop explicit (e.g., "if `agents sync --check` still fails, re-run `agents mcp test --runtime` and re-diagnose"). No bundle files exist, and none are needed at this size.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is 19 lines with zero padding: no concept explanations, no library overviews, and every line is either an executable command with its purpose or a concrete diagnostic priority. It fully assumes Claude's competence, matching the leanest anchor. | 5 / 5 |
Actionability | Every step is a copy-paste-ready command with exact flags (`agents status --fast`, `agents mcp test --runtime`, `agents doctor`, `agents sync --check`), and the priorities list gives concrete symptom categories to investigate. The diagnostic path is fully executable with no gaps. | 5 / 5 |
Workflow Clarity | The five steps are clearly ordered with an explicit verification checkpoint ("verify with `agents sync --check`") and a prioritized symptom checklist. It falls short of a 5 only because the error-recovery loop (what to do when verification still fails) is implicit rather than an explicit retry instruction. | 4 / 5 |
Progressive Disclosure | This is a sub-50-line skill with no bundle files and no need for external references; per the rubric's simple-skill guidance, well-organized sections alone warrant a 5. The two sections (diagnostic workflow, troubleshooting priorities) are cleanly separated and easy to navigate. | 5 / 5 |
Total | 19 / 20 Passed |