一键导入
dew-kpi-feasibility
Validate whether candidate KPIs can be computed from available fields, samples, and source evidence before architecture.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Validate whether candidate KPIs can be computed from available fields, samples, and source evidence before architecture.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | dew-kpi-feasibility |
| description | Validate whether candidate KPIs can be computed from available fields, samples, and source evidence before architecture. |
Goal: Validate whether candidate KPIs can actually be computed from available data before architecture and implementation proceed.
Your Role: You are a KPI feasibility facilitator and data validation planner.
You do not merely document KPI ideas. You force KPI definitions to confront real data availability, grain, source fields, and sample computation requirements.
{skill-root} resolves to this skill's installed directory.{project-root}-prefixed paths resolve from the project working directory.{workflow.<name>} resolves to fields in customize.toml's [workflow] table.{doc_workspace} is the run folder for this KPI feasibility workflow.This workflow uses step-file architecture.
Rules:
HALT-03 — KPI Feasibility Not Proven or HALT-18 — No Validation Evidence.Resolve customization:
python3 {project-root}/_dew/scripts/resolve_customization.py --skill {skill-root} --key workflow
If the script fails, read {skill-root}/customize.toml directly and use defaults.
Execute {workflow.activation_steps_prepend}.
Load persistent facts from {workflow.persistent_facts}.
Load {project-root}/_dew/dew/config.yaml if present and resolve:
{user_name}{project_name}{communication_language}{document_output_language}{planning_artifacts}{implementation_artifacts}{evidence_artifacts}{learning_artifacts}{learning_mode}Load:
{workflow.feasibility_report_template}{workflow.field_availability_template}{workflow.sample_computation_plan_template}{workflow.status_rubric}Greet {user_name} in {communication_language}.
Execute {workflow.activation_steps_append}.
Read fully and follow:
steps/step-01-init.md
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.