Knowledge Base Manager
Design and curate a maintainable knowledge base that grounds RAG or graph-based agents with provenance and versioned facts.
Overview
Knowledge Base Manager is an agent skill most often used in Build (also Validate, Operate) that designs, builds, and maintains curated knowledge bases for RAG, graphs, and human search.
Install
npx skills add https://github.com/daffy0208/ai-dev-standards --skill knowledge-base-managerWhat is this skill?
- Bridges document-based RAG and entity-based graph knowledge systems
- Decision framework for when KBs beat static docs or tiny FAQs
- Emphasizes curation, validation, versioning, and citation/provenance
- Targets AI systems needing grounded, verifiable answers
- Warns against unmaintained dumps that guarantee knowledge rot
- Explicit do/don't checklist for when to adopt knowledge bases vs static docs or FAQs under ~50 items
Adoption & trust: 1 installs on skills.sh; 29 GitHub stars; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
Your agent hallucinates or contradicts itself because scattered docs were never unified, versioned, or curated for grounded retrieval.
Who is it for?
Solo builders shipping RAG copilots, support agents, or domain assistants where facts change and citations matter.
Skip if: Under fifty static FAQs with no maintenance bandwidth, or projects where a simple docs site is sufficient.
When should I use this skill?
Building knowledge-intensive applications, managing organizational knowledge, or creating intelligent information systems that need structured, validated, accessible information.
What do I get? / Deliverables
You choose an appropriate KB architecture (document vs entity), define curation and provenance rules, and leave a maintainable system agents can query reliably.
- KB type decision (document RAG vs entity graph vs hybrid)
- Curation, versioning, and provenance guidelines
- Ingestion and reconciliation outline for multiple sources
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build/backend is the canonical shelf because the skill centers on structuring information systems, ingestion, and reconciliation—not one-off landing copy. Knowledge bases sit behind APIs, vector stores, and graph layers that solo builders wire during backend and agent integration work.
Where it fits
Decide whether your support-bot idea needs a curated KB or a 30-question FAQ before writing code.
Model entities and document chunks with citation metadata before wiring the retrieval API.
Establish review cadence and deprecation rules so agent answers do not drift after launch.
How it compares
Architecture and curation playbook for knowledge systems—not a drop-in vector DB installer or single MCP connector.
Common Questions / FAQ
Who is knowledge base manager for?
Developers and founders building AI products that must answer factual questions from organizational or product knowledge with consistency and traceability.
When should I use knowledge base manager?
In Validate when scoping a knowledge-heavy prototype; in Build when implementing RAG/graph storage and ingestion; in Operate when defining refresh cycles and preventing knowledge rot.
Is knowledge base manager safe to install?
The skill is methodological and does not mandate specific vendors; review the Security Audits panel on this page and audit any ingestion scripts or data pipelines you add locally.
SKILL.md
READMESKILL.md - Knowledge Base Manager
# Knowledge Base Manager Build and maintain high-quality knowledge bases for AI systems and human consumption. ## Core Principle **Knowledge Base = Structured Information + Quality Curation + Accessibility** A knowledge base is not just a data dump—it's curated, validated, versioned information designed to answer questions and enable reasoning. --- ## When to Use Knowledge Bases ### Use Knowledge Bases When: - ✅ Need to answer factual questions consistently - ✅ Information changes frequently and needs version control - ✅ Multiple sources need to be unified and reconciled - ✅ Provenance and citation tracking is critical - ✅ Building AI systems that need grounded, verifiable information - ✅ Organizational knowledge needs to be preserved and searchable - ✅ Complex domain with interconnected concepts ### Don't Use Knowledge Bases When: - ❌ Static documentation is sufficient (use docs + search) - ❌ No one will maintain/update it (knowledge rot guaranteed) - ❌ Simple FAQ covers all questions (<50 items) - ❌ Information doesn't change (static site faster/cheaper) - ❌ Team lacks resources for curation --- ## Knowledge Base Types: Decision Framework ### 1. Document-Based Knowledge Base (RAG) **What it is:** Collection of documents, chunked and embedded for semantic search **Best for:** - Technical documentation - Support articles, FAQs - Policy documents - Research papers - Blog content - User manuals **Strengths:** - Easy to add new documents - Preserves full context - Natural for text-heavy content **Weaknesses:** - Hard to query relationships ("Who works where?") - Duplicate information across documents - Difficult to keep facts consistent **Use:** `rag-implementer` skill + `vector-database-mcp` --- ### 2. Entity-Based Knowledge Base (Knowledge Graph) **What it is:** Network of entities (people, places, things) connected by relationships **Best for:** - Organizational charts - Product catalogs with relationships - Social networks - Recommendation systems - Fraud detection - Supply chain tracking **Strengths:** - Excellent for "how are X and Y related?" queries - Consistent facts (one source of truth) - Powerful traversal ("friends of friends") **Weaknesses:** - Upfront modeling required (ontology design) - Harder to add unstructured information - Learning curve for graph queries **Use:** `knowledge-graph-builder` skill + `graph-database-mcp` --- ### 3. Hybrid Knowledge Base (RAG + Graph) **What it is:** Documents for unstructured knowledge + Graph for structured entities/relationships **Best for:** - Enterprise knowledge management - Research with citations and relationships - Medical systems (documents + patient/drug relationships) - Legal systems (cases + precedents + entities) - E-commerce (products + specs + relationships) **Strengths:** - Best of both worlds - Flexible for different knowledge types - Rich querying capabilities **Weaknesses:** - Most complex to build and maintain - Requires expertise in both RAG and graphs - Higher infrastructure costs **Use:** Both `rag-implementer` + `knowledge-graph-builder` skills --- ## Decision Tree: Which KB Type? ``` What kind of knowledge do you have? ├─ Mostly unstructured text (docs, articles, content)? │ └─ Document-Based KB (RAG) │ Use: rag-implementer skill │ ├─ Mostly structured entities with relationships? │ └─ Entity-Based KB (Graph) │ Use: knowledge-graph-builder skill │ └─ Mix of both? └─ Hybrid KB (RAG + Graph) Use: Both skills + This skill for integration ``` --- ## 6-Phase Knowledge Base Implementation ### Phase 1: Knowledge Audit & Architecture **Goal**: Understand what knowledge ex