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 extremely lean, perfectly actionable redirect stub that delegates entirely to a shared external skill file. Conciseness, actionability, and workflow clarity are all maximal for a single-purpose skill. The only weakness is progressive disclosure: the skill contains no overview content of its own and its sole reference points outside the bundle, so the skill is unusable if that external path is absent.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is two lines with zero padding — a maintenance comment and a single directive — assuming Claude's competence with no re-explanation of known concepts, matching the 'lean and efficient; every token earns its place' anchor. | 5 / 5 |
Actionability | "Load and follow the shared skill at ~/.agents/skills/find-skills/SKILL.md" is a fully executable, unambiguous directive with a concrete path; per the rubric's scoring note, an instruction-only skill without code is not penalized when the guidance is this actionable. | 5 / 5 |
Workflow Clarity | This is a single-task skill and its one action (load and follow the shared skill) is unambiguous, which the rubric's simple-skill guideline allows to score 5; no destructive or batch operations are involved, so no validation cap applies. | 5 / 5 |
Progressive Disclosure | The reference is clearly signaled and one level deep, but the body is a pure redirect with no overview content, and the target (~/.agents/skills/find-skills/SKILL.md) lies outside the skill directory with no bundle files (no references/, scripts/, or assets/ exist) to back it — placing it between the 'some structure' and 'good structure' anchors, closer to 3 given the unverifiable external pointer. | 3 / 5 |
Total | 18 / 20 Passed |