Content
100%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.
An exemplary deprecation stub: it explicitly disclaims itself, names the replacement, and tells stale references how to update. The rubric's simple-skill and instruction-only scoring notes support top marks on every dimension.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is five lean lines with zero padding and no explanation of concepts Claude already knows — every token ('This skill has been renamed. **Do not follow any instructions here...**', 'Invoke the **`snippets`** skill instead') earns its place for the redirect. | 5 / 5 |
Actionability | The guidance is fully executable for an instruction-only skill: 'Invoke the **`snippets`** skill instead' and 'update it from `aiconfig-snippets` to `snippets`' are concrete, unambiguous actions covering both common cases (an agent landing here, and a stale reference needing renaming). No gaps to a score of 4's 'minor gaps' anchor can be identified. | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill whose single action (redirect to `snippets`) is unambiguous, so the simple-skill exception applies and workflow clarity scores 5; no destructive or batch operations exist to trigger the validation cap. | 5 / 5 |
Progressive Disclosure | The body is under 50 lines, requires no external references (no references/, scripts/, or assets/ bundle files exist), and is well organized with a clear heading and one-level structure, satisfying the simple-skill exception. | 5 / 5 |
Total | 20 / 20 Passed |