signal-taxonomy
用于为丰富数据定义模式、主题标签和谱系元数据
📖 中文导读:用于为丰富数据定义模式、主题标签和谱系元数据 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。
name: signal-taxonomy description: Use to define schemas, topic tags, and lineage metadata for enriched signals.
Signal Taxonomy Skill
When to Use
- Normalizing multiple provider outputs into a unified schema.
- Rolling out new intent topics, enrichment attributes, or scoring dimensions.
- Auditing lineage + compliance requirements.
Framework
- Schema Definition – fields, datatypes, required/optional flags.
- Topic & Attribute Mapping – align provider-specific attributes to canonical names.
- Versioning – maintain change logs, effective dates, and migration steps.
- Validation Rules – min/max values, allowed lists, dependency rules.
- Documentation – publish data dictionary + lineage diagrams.
Templates
- Data dictionary sheet (field, description, source, owner).
- Topic mapping table by provider.
- Migration checklist for schema changes.
Tips
- Keep names human-readable for GTM teams but consistent with data warehouse standards.
- Tag every field with owner + refresh cadence.
- Pair with
identity-resolutionto ensure IDs and linkages stay consistent.