agentsclimarketplace

Data catalog enricher

Skill a5c-ai/babysitter/library/specializations/data-engineering-analytics/skills/data-catalog-enricher

Enriches data catalog entries with automated metadataFrom its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill data-catalog-enricher

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.9 KB, 294 tokens by cl100k_base, as published. Nobody here has run it

Data Catalog Enricher

Overview

Enriches data catalog entries with automated metadata. This skill enhances data discoverability and governance through intelligent metadata augmentation.

Capabilities

  • Automated tag suggestion
  • Business glossary term matching
  • Owner/steward recommendation
  • Usage pattern analysis
  • Data classification (sensitivity, PII)
  • Quality score integration
  • Lineage enrichment
  • Search optimization

Input Schema

{
  "catalogEntry": "object",
  "dataProfile": "object",
  "existingGlossary": "object",
  "organizationContext": "object"
}

Output Schema

{
  "enrichedEntry": "object",
  "suggestedTags": ["string"],
  "glossaryMatches": ["object"],
  "classificationResults": "object",
  "ownerSuggestions": ["string"]
}

Target Processes

  • Data Catalog
  • Data Lineage Mapping
  • Data Quality Framework

Usage Guidelines

  1. Provide existing catalog entry for enrichment
  2. Include data profile for classification analysis
  3. Supply business glossary for term matching
  4. Add organization context for owner recommendations

Best Practices

  • Regularly update glossary matches as glossary evolves
  • Validate PII classifications with data stewards
  • Integrate quality scores from quality framework
  • Maintain consistent tagging taxonomy
  • Review and approve automated classifications

What ships with it: 1 file

481 B alongside SKILL.md

Keep looking

Skills are one crate of 326,059. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.