From omni
四维评分量规(业务价值、技术完整性、清晰度与可测性、可追溯性)用于评估 Spec 产出物内容质量,定义检查项、打分标准及 YAML 报告格式。由 evaluation-analyst 引用,适用于 spec_eval 模式。
How this skill is triggered — by the user, by Claude, or both
Slash command
/omni:evaluation-rubricThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
当前仅定义 **spec_eval** 模式的量规。design_eval、detail_eval 的量规待后续扩展。
当前仅定义 spec_eval 模式的量规。design_eval、detail_eval 的量规待后续扩展。
评估内容:
检查项:
典型扣分项:
打分参考:
评估内容:
检查项:
典型扣分项:
打分参考:同维度 1
评估内容:
检查项:
典型扣分项:
打分参考:同维度 1
评估内容:
检查项:
典型扣分项:
打分参考:同维度 1
每个 finding 必须包含以下字段:
| 字段 | 类型 | 说明 |
|---|---|---|
| severity | string | info | warning | error |
| location | string | 问题位置(章节名、FR 编号、用户故事编号等) |
| message | string | 问题描述 |
| recommendation | string | 改进建议 |
| line | number | null | 行号(可选,无法定位时为 null) |
| gene_related | string | null | 若问题位置与 Genome Usage Metadata 中某基因的 locations 匹配,填写该 gene_id;否则为 null |
| gene_contribution | string | null | 当 gene_related 非空时必填:positive(基因预填充有助于质量)、negative(基因预填充导致或加剧问题)、neutral(与基因无关或无法判断) |
severity 分级:
specs/{feature}/.runs/evaluations/evaluation-report.yaml
YAML 报告需带详细注释(# 开头),便于人工阅读和配置调整。每个主要区块应有分隔注释说明用途。
npx claudepluginhub zte-aicloud/co-omnispec --plugin omniAudits specification files for quality against a rubric covering structure, requirements, acceptance criteria, traceability, and quality; generates A-F graded reports with issues and recommendations.
Reviews completed requirement spec drafts via structured rubric and checklist, assessing clarity, testability, acceptance criteria, assumptions, and approval readiness for design phase.
Reviews spec.md files for completeness, clarity, implementability, testability, and structure. Identifies ambiguities, gaps, and missing sections before implementation.