Content
96%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 model deprecation stub: minimal, unambiguous, and immediately actionable, telling the reader both what not to do and exactly where to go. Its only imperfection is cosmetic — a flat structure with no sections, which barely matters at five lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Five lean lines with no padding and no explanation of concepts Claude already knows — every token earns its place in delivering the redirect. | 5 / 5 |
Actionability | The instruction is fully executable: "Invoke the `tools` skill instead" plus a concrete remediation step ("update it from `aiconfig-tools` to `tools`") with no ambiguity about what to do. | 5 / 5 |
Workflow Clarity | A single, unambiguous action with an explicit guard ("Do not follow any instructions here"); the simple-skill exception applies and there are no destructive or batch operations requiring validation. | 5 / 5 |
Progressive Disclosure | The pointer to the `tools` skill is well-signaled and exactly one level deep, which is the right structure for a stub; the only minor gap is the flat paragraph layout with no sectional organization, though none is strictly needed at this size. | 4 / 5 |
Total | 19 / 20 Passed |