knowledge-base-manager
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.
What this skill does
# 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
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.