Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ontology-of-everything/semantic-creator
Builds evidence-only Kimball semantic layers from APIs, CLIs, or tables with an HTML decision workbench; emits OKF/YAML.
Passed 23 of 25 test cases with the skill, and 12 of 25 without it.
and 11 more in the full report
12 fixed11 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
A test case the skill fixed. Same model, same prompt, with and without the skill.
在 Phase 2 Review 收到用户的修订反馈并写入 amendments 后,模型构建流程要求在重新出具评审报告前执行什么动作?
| Checked | Without skill | With skill |
|---|---|---|
| Re-generates the review report before seeking user approval | Missed | Passed |
The instructions your model reads when the skill loads.
把接口契约(REST/OpenAPI、CLI、表/DDL)一次通过地建成受治理语义层。四个阶段严格串行,每阶段一个参考文件、一组退出条件——满足才前进,不满足不硬闯:
Phase 1 Ingest → Phase 2 Review → Phase 3 Emit → Phase 4 Verify
ingest.md review.md emit-okf.md verify.md
emit-yaml.md
唯一真源是接口。不臆造字段/粒度/枚举/取值;缺证据停下,一次一问。
references/ingest.md)接口归一成「操作清单」,每个 op 判定角色(fact / dimension-lookup)。 退出条件:清单完整,每个 op 有角色与读写标记。
references/review.md)将对象拆为原子决策;显式展示目标、候选、证据、风险、依赖与权衡,并在
事实、维度、度量、路由分区提供固定 YAGNI 判断指导。生成 model JSON 注入
assets/review-template.html,由用户确认、选择、修正、补证或拒绝;反馈写入
amendments.md 后重出报告。
退出条件:收到 approved:true,且无未决或阻塞项。出报告后必须停下;
未批准禁止进入 Phase 3。
references/emit-okf.md 默认 / references/emit-yaml.md 可选)默认生成 Google OKF v0.1 bundle;用户明确要求时生成 repo-YAML(Kimball 星型)。字段语义两个目标共享(定义在 emit-yaml.md §2–§4)。≥2 个 bundle 时生成薄根索引。
退出条件:产物文件完整落盘。
references/verify.md)跑结构检查 + 语义 lint +(如导出 OKF)OKF 硬约束,逐条回报 pass/fail。 退出条件:全部 pass;不可机械修复的 fail → 回 Phase 2 One blocking ask,不静默通过。
test cases passed, vs 12 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.