メニュー
Update the knowledge graph with new or changed markdown files. Re-ingests documents, extracts from new chunks, and resolves new duplicates. Use when the user has added, edited, or removed markdown files and wants the graph updated.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Build a knowledge graph from markdown files. Ingests documents, extracts entities and relations, resolves duplicates, and induces a typed schema. Use when users want to create a knowledge graph, index their documents, or extract structured data from markdown files.
Explore and query the knowledge graph interactively. Search for topics, investigate entities, trace connections, and discover patterns. Use when users want to ask questions about their knowledge graph, find connections, or understand relationships in their documents.
| name | reindex |
| description | Update the knowledge graph with new or changed markdown files. Re-ingests documents, extracts from new chunks, and resolves new duplicates. Use when the user has added, edited, or removed markdown files and wants the graph updated. |
This skill incrementally updates an existing knowledge graph when documents have changed. Only new or modified files are processed.
Use the kgmd MCP server tools: ingest_documents, get_chunks_for_extraction, store_extractions, get_resolution_candidates, apply_merges.
Call ingest_documents(). It automatically:
Report: how many documents were new, updated, or skipped.
If new chunks were created:
get_chunks_for_extraction(batch_size=10)store_extractions() with resultsget_resolution_candidates() — new entities may duplicate existing onesapply_merges()Summarize what changed: