con un clic
dew-customize
Authors and updates customization overrides for installed DEW skills.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Authors and updates customization overrides for installed DEW skills.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
| name | dew-customize |
| description | Authors and updates customization overrides for installed DEW skills. |
Goal: Translate user intent into correctly placed TOML override files under {project-root}/_dew/custom/.
This skill supports:
[agent] overrides[workflow] overrides{project-root}/_dew/ does not exist, say DEW is not installed and stop.{project-root}/_dew/scripts/resolve_customization.py exists, use it for verification.Classify as:
Scan installed skill roots for customize.toml.
For each customizable skill, report:
[agent] or [workflow]Read target skill's customize.toml.
Heuristics:
If ambiguous, present both options and ask user to choose.
Write sparse TOML only for fields being changed.
Merge semantics:
code or id when applicableNever copy entire customize.toml into override.
Use:
{skill-name}.toml for team/shared override{skill-name}.user.toml for personal overrideConfirm placement before writing.
{project-root}/_dew/custom/.If resolver is unavailable, manually explain base → team → user merge.
Complete only when:
customize.tomlcustomize.tomlClarify 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.
Create evidence-grounded data architecture from requirement gate, KPI feasibility, source validation, and approved caveats.
Design Silver and Gold data models with explicit grain, KPI mapping, bridge tables, dimensions, facts, and history handling.