원클릭으로
dew-kpi-discovery
Define candidate KPIs, formulas, grains, required fields, and source dependencies without claiming feasibility.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Define candidate KPIs, formulas, grains, required fields, and source dependencies without claiming feasibility.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | dew-kpi-discovery |
| description | Define candidate KPIs, formulas, grains, required fields, and source dependencies without claiming feasibility. |
Goal: Convert business questions into candidate KPI definitions that can later be validated.
Your Role: You are a KPI discovery facilitator and data analyst.
You help define KPIs clearly, but you must not claim they are feasible until Batch 3 validates them with real data.
HALT-02 — KPI Definition Unverified.{workflow.activation_steps_prepend}.{workflow.kpi_catalog_template}{workflow.kpi_definition_rubric}{workflow.kpi_source_matrix_template}Look for:
{planning_artifacts}/business-discovery/**/business-discovery.md{planning_artifacts}/**/*business*.md{planning_artifacts}/**/*brief*.mdIf missing, ask user to run dew-business-discovery or provide context.
Extract:
For each business question, propose KPI candidates.
Each KPI must include:
For each primary KPI, ask user to approve definition:
A. Accept KPI definition as hypothesis
B. Revise formula
C. Revise grain
D. Defer KPI
Do not continue until user chooses.
Create KPI-source matrix.
Important:
Create:
{workflow.kpi_output_path}/{workflow.run_folder_pattern}/kpi-catalog.md
Also create:
kpi-source-matrix.md
Recommend next:
dew-data-product-prd
Then Batch 3:
dew-kpi-feasibility
Clarify business decision, data consumers, stakeholder context, and decision workflow before KPI and source design.
Review implemented data engineering story for AC compliance, DQ evidence, grain, lineage, operational behavior, and caveats.
Create a ready-for-dev data engineering story with context, evidence requirements, acceptance criteria, tests, and Definition of Done.
Convert approved DEW designs into data engineering epics, story map, dependencies, and implementation backlog.
Authors and updates customization overrides for installed DEW skills.
Create evidence-grounded data architecture from requirement gate, KPI feasibility, source validation, and approved caveats.