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 an exemplary minimal redirect skill: exact output text, exact delegation instruction with argument passthrough, explicit ordering, and a scope guard, with zero padding. It fully leverages the simple-skill exceptions in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Thirteen lean lines: one sentence of rename context ("Most AI tools keep /help for a command of their own..."), the exact line to print, the delegation instruction, and a closing scope guard. Every token earns its place and nothing explains concepts Claude already knows. | 5 / 5 |
Actionability | The guidance is fully executable: the output line is given verbatim ("/help is now /next-step. Running /next-step."), the tool to call is named ("Run the next-step skill with the Skill tool"), and argument passthrough is specified precisely ("passing these arguments unchanged (none, if this is empty): $ARGUMENTS"). Per the scoring notes, an instruction-only skill with this specificity earns full marks. | 5 / 5 |
Workflow Clarity | Two numbered steps with an explicit ordering constraint ("as the first line of your reply") and a scope guard ("Do nothing else here: /next-step does the work"). The simple-skill exception applies: the single action is unambiguous, and no destructive or batch operations require validation checkpoints. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references, and is well organized (header, one sentence of context, numbered steps, scope guard); no bundle files exist. Per the guideline, this earns a 5 with just well-organized sections. | 5 / 5 |
Total | 20 / 20 Passed |