knowledge-base-manager — Claude Code skill for knowledge bases
knowledge-base-manager is a Claude Code skill for choosing a document, graph, or hybrid knowledge-base design and planning its maintenance. It covers content curation, quality checks, and versioning.
MIT 131 installs ★ 29 updated 2026-08-17
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a claude-codeWhat knowledge-base-manager does
This skill gives you a method for choosing a knowledge-base architecture based on query patterns. Document-based designs fit material such as manuals and FAQs; graph-based designs suit questions about relationships between entities. A hybrid combines the two, with added complexity.
Its guidance covers auditing sources, curating and cleaning content, measuring quality, versioning, and maintenance governance. It also recommends checking the knowledge base against real user questions and tracking freshness. Use rag-implementer for retrieval pipelines, or knowledge-graph-builder to implement a knowledge graph; this skill focuses on architecture and governance rather than those implementation tasks.
What it helps with
- choose a knowledge-base architecture for query patterns
- set up a content curation workflow
- test knowledge quality against user questions
- plan versioning and change audits
- schedule freshness checks for knowledge
Example prompts for the agent
- Choose a knowledge-base design for manuals, FAQs, and questions about entity relationships.
- Draft a workflow to curate and quality-check content for this knowledge base.
- Suggest versioning and freshness-monitoring practices for our knowledge base.
How to install knowledge-base-manager
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a claude-code2Manually: put the files in place
~/.claude/skills/knowledge-base-manager/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/knowledge-base-manager/
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a codex2Manually: put the files in place
.agents/skills/knowledge-base-manager/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a cursor2Manually: put the files in place
.cursor/skills/knowledge-base-manager/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install oakoss/agent-skills skills/knowledge-base-manager2Manually: put the files in place
.github/skills/knowledge-base-manager/SKILL.md1Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a gemini-cli2Platform CLI
gemini skills install https://github.com/oakoss/agent-skills --path skills/knowledge-base-managerManually: put the files in place
.devin/skills/knowledge-base-manager/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add oakoss/agent-skills --skill knowledge-base-manager -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about knowledge-base-manager
How do I install knowledge-base-manager in Claude Code?
Run npx skills add oakoss/agent-skills --skill knowledge-base-manager -a claude-code. The skill file is at ~/.claude/skills/knowledge-base-manager/SKILL.md.
What does knowledge-base-manager do?
It helps select a knowledge-base architecture and plan content curation, quality measurement, versioning, and ongoing governance.
When should I use a hybrid knowledge base?
Use it when queries need both document search and traversal across entity relationships. The skill identifies this architecture as the most complex option.
Source text
SKILL.md · MIT
--- name: knowledge-base-manager description: 'Knowledge base architecture selection, curation, and governance. Use when choosing between document-based (RAG), entity-based (graph), or hybrid KB architectures, establishing content curation workflows, implementing versioning and governance, or evaluating quality metrics. For building retrieval pipelines, use the rag-implementer skill. For building knowledge graphs, use the knowledge-graph-builder skill.' license: MIT metadata: author: oakoss version: '1.1' --- # Knowledge Base Manager ## Overview Provides a structured methodology for selecting, designing, and governing knowledge bases. Covers architecture decisions (document-based vs entity-based vs hybrid), content curation, quality metrics, versioning strategies, and maintenance governance. Use when choosing a KB architecture, establishing curation workflows, or building governance processes for organizational knowledge. **When NOT to use:** Static documentation suffices, fewer than 50 FAQ items cover all questions, or no maintenance resources are available. For implementing retrieval pipelines (chunking, embeddings, vector stores), use the `rag-implementer` skill. For implementing knowledge graphs (ontology, entity extraction, graph databases), use the `knowledge-graph-builder` skill. ## Quick Reference | Aspect | Options | Key Considerations | | ---------------------- | -------------------------------------------------- | ------------------------------------------------------------------ | | **Architecture** | Document-based (RAG), Entity-based (Graph), Hybrid | Match to query patterns; start simple, add complexity when needed | | **Document-based** | Vector DB (Pinecone, Weaviate, pgvector) | Best for docs, FAQs, manuals; semantic search; easy to add content | | **Entity-based** | Graph DB (Neo4j, ArangoDB) | Best for org charts, catalogs, networks; relationship traversal | | **Hybrid** | Both + linking layer | Enterprise, medical, legal; combined queries; highest complexity | | **When to skip KB** | Static docs, <50 FAQ items | No maintenance resources, information never changes | | **Implementation** | 6 phases | Audit, Curation, Storage, Quality, Versioning, Governance | | **Accuracy target** | >90% on test questions | Create 100+ test questions with known correct answers | | **Coverage target** | >80% questions answerable | Validate against real user queries continuously | | **Freshness target** | <30 days average age | Automated freshness monitoring + scheduled updates | | **Consistency target** | >95% conflict-free | Deduplication + single source of truth | | **Query latency** | <100ms median | Caching and optimization for common access patterns | | **Storage tech** | pgvector, Pinecone, Weaviate, Chroma | pgvector for existing Postgres; Pinecone for managed scale | | **Index types** | HNSW, IVFFlat | HNSW for recall; IVFFlat for frequently rebuilt indexes | | **Ingestion pipeline** | Load, clean, chunk, embed, store | Chunk at semantic boundaries; 512 tokens max; 10-15% overlap | | **Deduplication** | Content hashing, semantic similarity | Hash for exact dupes; cosine similarity >0.95 for semantic dupes | | **Quality testing** | Recall@K, MRR, accuracy sampling | 100+ test questions; measure recall@10 >0.8 and MRR >0.7 | | **Drift detection** | Embedding distribution monitoring | Track mean shift; alert when >0.1 threshold | | **Versioning** | Snapshot, Event-sourced, Git-style | Snapshot for simple; event-sourced for audit; git-style for teams | | **Maintenance** | Daily, Weekly, Monthly, Quarterly | Establish schedule from day 1; monitor errors and user feedback | ## Common Mistakes | Mistake | Correct Pattern | | ---------------------------------------------------------- | -------------------------------------------------------------------------------------- | | Ingesting raw data without curation or normalization | Curate, clean, and deduplicate before ingesting; quality over quantity | | Skipping version control for KB content | Implement versioning from day one with rollback and audit trail | | Building a KB without validating against user questions | Start with user research and test against real queries for >90% accuracy | | Choosing hybrid architecture when document-based suffices | Match architecture to actual query patterns; start simple, add complexity when needed | | Launching without freshness monitoring or update schedules | Set up automated freshness checks and scheduled content reviews | | No provenance tracking on knowledge entries | Always track source URL, timestamp, author, and confidence score | | Duplicate information across sources | Establish single source of truth; merge similar entries with conflict resolution rules | | Perfectionism delaying launch | Launch at 80% coverage and iterate based on real usage data | ## Delegation - **Audit existing knowledge sources and classify content types**: Use `Explore` agent to inventory documents, assess quality, and identify gaps - **Implement end-to-end KB pipeline with storage and retrieval**: Use `Task` agent to deploy database, configure search, and run quality checks - **Design KB architecture and governance model**: Use `Plan` agent to select between document-based, entity-based, or hybrid approaches > For implementing document retrieval pipelines (chunking, embeddings, vector stores, hybrid search), use the `rag-implementer` skill. For implementing knowledge graphs (ontology design, entity extraction, graph databases), use the `knowledge-graph-builder` skill. ## References - [Architecture and Types](references/architecture.md) -- KB types, decision framework, knowledge classification - [Curation and Ingestion](references/curation.md) -- extraction, cleaning, deduplication, provenance tracking - [Storage and Retrieval](references/storage.md) -- database selection, interfaces, technology stacks - [Quality Control](references/quality-control.md) -- metrics, validation strategies, continuous monitoring - [Versioning](references/versioning.md) -- snapshot, event-sourced, and git-style approaches - [Governance](references/governance.md) -- maintenance schedules, roles, change processes
© oakoss · MIT · oakoss/agent-skills