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 lean instruction skill: it frames the persona, lists exactly which inputs to gather, provides a complete copy-paste output template, and gives quantified hiring-trigger examples. Every section earns its place and the single task is unambiguous, so all dimensions land at the top anchor.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~50-line body has zero padding: a two-sentence role frame ("People Ops 디렉터처럼 본다. 지금 뽑아야 할 사람과 나중에 뽑아야 할 사람을 구분한다."), a five-bullet input list, an output template, and three trigger examples. Nothing explains concepts Claude already knows, matching anchor 5 ('every token earns its place') rather than anchor 4's 'minor instances of over-explanation'. | 5 / 5 |
Actionability | The 출력 형식 template is copy-paste ready with exact table schemas ("| 역할 | 왜 필요한가 | 지금/나중 | 고용 형태 | 월 비용 가정 |") and the trigger examples are quantified ("주간 개발 병목이 2주 이상 지속되면", "CAC 실험이 3개 이상 동시 진행되면") covering common cases. Per the instruction-only scoring note this is fully actionable guidance, not anchor 4's 'minor gaps'. | 5 / 5 |
Workflow Clarity | This is a single-task, non-mutating skill (frontmatter: "mutating: false") whose one action is unambiguous: the input list ("비즈니스 모델", "개발 로드맵", "GTM/세일즈 플랜", "창업자 역량", "자금 상황") and exact output template leave no doubt about what to do, so the simple-skill exception applies. No destructive or batch operations exist, so the validation cap does not apply; below 5 would require sequence gaps or ambiguity that are absent. | 5 / 5 |
Progressive Disclosure | A short (~1.2KB) self-contained skill with no bundle files: the four sections (역할, 입력, 출력 형식, 채용 트리거 예시) are well-organized and no content belongs in a separate file, matching the guideline that skills of this size with no need for external references score 5 on well-organized sections alone. | 5 / 5 |
Total | 20 / 20 Passed |