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.
An exemplary minimal instruction-only skill: lean, specific, and unambiguous, with no padding and no need for bundled references. The only gap is the absence of illustrative examples for common cases, which caps actionability at 4.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and efficient — three short directives with zero concept explanation or padding — and assumes Claude's competence, matching the 'every token earns its place' anchor exactly. | 5 / 5 |
Actionability | Directives are concrete and specific ('Treat the question as genuine curiosity, not an accusation', 'If you do not know, say so plainly'), but no examples illustrate how to handle common cases, keeping it just below the fully-executable-with-examples anchor. | 4 / 5 |
Workflow Clarity | This is a simple single-task skill where the action — answer genuinely, give candid facts, admit ignorance — is unambiguous, so the simple-skill exception applies; no destructive or batch operations trigger the validation cap. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references (none of the bundle directories contain files), and is well-organized as short directives, satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 19 / 20 Passed |