菜单
Analyzes current DEW state and user query to recommend the next skill(s) or answer workflow questions.
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-help |
| description | Analyzes current DEW state and user query to recommend the next skill(s) or answer workflow questions. |
Help the user understand where they are in the DEW workflow and what to do next.
When this skill completes, the user should:
{project-root}/_dew/_config/dew-help.csv — assembled manifest of installed DEW skills.{project-root}/_dew/config.yaml and user overrides when present.outputs patterns at resolved output-location paths.project_knowledge resolves to an existing path, read it for grounding context._meta rows in module catalogs may point to documentation.Catalog format:
module,skill,display-name,menu-code,description,action,args,phase,preceded-by,followed-by,required,output-location,outputs
Phases:
anytime — available regardless of workflow state.Sequencing:
preceded-by — skills that should ideally complete before this one.followed-by — skills that should ideally run after this one.skill-name or skill-name:action.Required gates:
required=true items must complete before moving meaningfully to later phases.Completion detection:
outputs patterns.For each recommended item, present:
[menu-code] Display nameShow optional items first, then the next required item. Keep the response focused.
{communication_language} when available.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.