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.
An exemplary SKILL.md body: fully directive, quantified guidance with a copy-paste output contract and an explicit self-check validation step. The only minor gap is that the body sits slightly over the simple-skill line length with no offloaded reference material.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and directive throughout — "Pick a topic", "Lay out three regions", with hard numbers ("240–280px", "350 words", "5–15 lines") and zero explanation of concepts Claude already knows. Every line earns its place. | 5 / 5 |
Actionability | Guidance is fully concrete and executable for the common case: exact pixel ranges, named CSS logical properties ("margin-inline-start", "inset-inline-end"), quantified prose requirements, and a copy-paste <artifact> output template. No pseudocode or vague direction. | 5 / 5 |
Workflow Clarity | Steps 1–6 form a clear sequence ending in an explicit Self-check checklist (line length, mono token usage, accent restraint, responsive behavior). The operation is generative rather than destructive, so no error-recovery loop is required. | 5 / 5 |
Progressive Disclosure | No bundle files exist, and the ~54-line body is well organized into Workflow and Output contract sections with no buried references. It falls just short of the simple-skill 5 threshold because the body slightly exceeds 50 lines and a few self-check details could plausibly live in a separate reference file. | 4 / 5 |
Total | 19 / 20 Passed |