Content
78%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.
A clean, well-organized instruction skill that stays lean and gives concrete writing rules. It would benefit from tightening the obvious Process steps and adding a worked input->output example.
Suggestions
Tighten the Process section: 'Read and understand' and 'Plan the rewrite' restate what Claude already does; fold them into a single concise step or drop them.
Add a short worked example (original request -> rewritten prompt) so the transformation is concrete and copy-paste ready.
Optionally add an explicit output self-check (e.g., verify length is within 0.75X-1.5X and contains no invented information) to give the workflow a concrete checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, but the Process steps ('Read and understand', 'Plan the rewrite') are mildly over-explanatory of obvious actions; not a 5 because of those minor padding instances, not a 3 because the bulk earns its place. | 4 / 5 |
Actionability | Concrete, specific guidance (0.75X-1.5X length, no emojis, '-' not '*', heading rules) is actionable for an instruction-only skill; not a 5 because it lacks an input->output example showing the transformation, which would make it copy-paste ready. | 4 / 5 |
Workflow Clarity | A clear 3-step sequence (read, plan, rewrite) is given and the task is non-destructive so no validation cap applies; not a 5 because the steps are somewhat generic rather than unambiguous checkpoints. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references and well-organized sections (Core Task, Process, Writing Guidelines, Output), satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |