KGRAG

Claude_T orchestrator skill — complete tool decision tree AND CLI reference for the full KGRAG fleet: PyCodeKG, DocKG, MemoryKG, DiaryKG, FTreeKG, AgentKG, MetaboKG, GutenbergKG, IAKG. Use this skill when working in any KGRAG-enabled repo or when the user asks about code, documents, diary, memory, metabolism, filesystem trees, Gutenberg/IA corpora, or self-knowledge queries — via MCP tools or CLI.

Step-by-step release workflow for publishing code-kg to PyPI using Poetry. Use this skill when the user wants to cut a release, bump the version, update the CHANGELOG, tag a commit, build and publish to PyPI, or run any part of the release pipeline for the code-kg project.

Scaffold a complete new KGModule package for any knowledge domain. Use when the user wants to build a new domain knowledge graph using the KGModule SDK (e.g. "build a file tree KG", "create a TypeScript KG module", "scaffold a new KG for genomics data"). Invoked as "/new-kg-module NAME" where NAME is the snake_case package name (e.g. filetreekg, tskg, genomicskg).

Use KGRAG to query across federated knowledge graphs (code, docs, metabolic) and manage cross-KG registries. Triggers when: searching multiple repos/KGs simultaneously, initializing KGs in new repos, querying code patterns across projects, extracting multi-KG snippets, or managing registry status.