Content
92%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 an exemplar of token efficiency: a crisp four-step workflow with an explicit stop rule and clean boundaries to sibling skills, all in seven lines. The only minor gap is the absence of a short example exchange, which keeps actionability at 4.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and telegraphic — "One exchange: readings out, pick back." — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching anchor 5. | 5 / 5 |
Actionability | Directives are concrete and executable — "each ending in what it would build or do differently", "name the source", "Take the pick as the confirmed ask and restate it" — but no example exchange shows the output form. For an instruction-only skill this matches anchor 4 (minor gaps) rather than 5 (no example covering the common case). | 4 / 5 |
Workflow Clarity | The sequence is unambiguous — name readings, drop ones a source rules out, ask the user to pick, restate the pick — with an explicit stop-condition: "If the user cannot pick, the words are not the problem — stop." As a single-task skill under 50 lines with a clear checkpoint, it matches anchor 5. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external files (no references/, scripts/, or assets/ exist), and is organized into clear short paragraphs with explicit routing to the interrogate and elicit skills. Per the simple-skill guideline, well-organized sections alone earn anchor 5. | 5 / 5 |
Total | 19 / 20 Passed |