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.
The body is a model of lean, fully actionable instruction for a simple skill: exact tool name, exact presentation requirements with rationale, and a concrete follow-up, all in one sentence. Nothing is missing for the task it describes and nothing is extraneous.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The single sentence packs in exactly the needed instructions — which tool to call, how to present the output, why ("so the columns stay aligned"), and one follow-up action — with zero padding or explanation of concepts Claude already knows. Every token earns its place, matching 'Lean and efficient; assumes Claude's competence'. | 5 / 5 |
Actionability | It names the exact tool (`mcp__context_mode__ctx_stats`), the exact output handling ("show the text block of its reply to the user unchanged, inside a code block"), and a concrete follow-up ("one sentence under it that names the largest saving") — fully executable, specific guidance that covers the entire task. As an instruction-only skill, no code is expected and the guidance is unambiguous. | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill where the single action is unambiguous: call the tool, render its reply verbatim in a code block, add one summarizing sentence. The rubric's simple-skill exception applies, and no destructive or batch operations exist that would require validation checkpoints. | 5 / 5 |
Progressive Disclosure | The skill is well under 50 lines with no need for external references — the entire procedure is complete in one self-contained instruction with no references/, scripts/, or assets/ bundle present. Per the rubric guideline, a short skill with no need for external references scores 5 on organization. | 5 / 5 |
Total | 20 / 20 Passed |