Content
45%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 perfectly lean but content-free: 'Do the thing.' gives Claude no actionable or workflow-level guidance, making the skill unusable in practice. Only its trivially clean structure avoids a floor score on every dimension.
Suggestions
Replace 'Do the thing.' with concrete, executable guidance — actual commands, code, or specific instructions for the task.
If the task involves multiple steps, sequence them explicitly with a validation checkpoint; even a single-step skill must state its one action unambiguously.
State expected inputs and outputs so Claude can verify it performed the task correctly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is two lines with zero padding or explanation of concepts Claude already knows; nothing present is unnecessary, matching the 'lean and efficient' anchor. | 5 / 5 |
Actionability | The only instruction is 'Do the thing.', which is entirely vague — it describes rather than instructs, with no concrete code, commands, or specific steps. | 1 / 5 |
Workflow Clarity | No steps or sequence are given, and the single action is maximally ambiguous, so the simple-skill exception (which requires an unambiguous single action) does not apply. | 1 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references (none exist in the bundle), and the minimal content is trivially well-organized under a single matching header, satisfying the rubric's simple-skill provision. | 5 / 5 |
Total | 12 / 20 Passed |