Enrich

This is the grounding layer for your Claude agent. It walks you through adding knowledge sources so your agent stops hallucinating and starts citing facts. The skill covers RAG pipelines with chunking strategies, structured database queries, and real-time API integrations. It includes a knowledge source assessment table and forces you to think about attribution, fallbacks, and refresh strategies. The best part is the knowledge systems reference it points to in the agent workflow skill for deeper RAG architecture. Use this when your agent needs to work with docs, codebases, databases, or external APIs. The mandatory preparation step ensures you've got workflow context before adding knowledge sources.

skills.sh installs: 326
GitHub stars: 602
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add sharpdeveye/maestro --skill enrich --agent claude-code

Installs into .claude/skills of the current project.

Files

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the knowledge-systems reference in the agent-workflow skill for RAG architecture, chunking strategies, and retrieval patterns.

Add knowledge sources to ground the workflow in facts. Without grounding, agents hallucinate. With grounding, they cite sources.

Knowledge Source Assessment

Identify what knowledge the workflow needs:

Knowledge Type	Source	Update Frequency	Access Pattern
Domain docs	Internal docs, specs	Monthly	Semantic search
Code context	Codebase	Real-time	Code search
User data	Database, CRM	Real-time	Structured query
External data	APIs, web	Real-time	API call
Historical	Logs, past interactions	Daily	Time-range query