Kg Extract
技能 已验证 活跃Extract entities and relations from source files to build a knowledge graph
To automatically build and update a knowledge graph from source code, aiding in codebase understanding, dependency analysis, and impact assessment.
功能
- Extracts entities like classes, functions, and modules
- Identifies relations such as imports, extends, and calls
- Stores extracted data as a knowledge graph in AgentDB
- Provides CLI alternatives for direct interaction
使用场景
- Building a knowledge graph for a new codebase
- Updating an existing knowledge graph with new code
- Analyzing codebase dependencies and structure
- Assessing the impact of code changes
非目标
- Executing code
- Performing static analysis beyond entity and relation extraction
- Managing the AgentDB instance itself
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-knowledge-graph@ruflo质量评分
已验证类似扩展
Understand Domain
100从代码库中提取业务领域知识并生成交互式领域流程图。可独立运行（轻量级扫描）或从现有的 /understand 知识图中派生。
Understand
100分析代码库以生成交互式知识图谱，用于理解架构、组件和关系
Understand Knowledge
100分析 Karpathy 模式的 LLM Wiki 知识库，并生成一个交互式知识图谱，包含实体提取、隐含规则和主题聚类。
Agentdb Query
99Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
Metal
100Extract the conceptual essence of a repository as skills, agents, and teams — the project's roles, procedures, and coordination patterns expressed as agentskills.io-standard definitions. Reads an arbitrary codebase and produces generalized definitions that capture WHAT the project does and WHO operates it, without replicating HOW it does it. Use when onboarding to a new codebase and wanting to understand its conceptual architecture, when bootstrapping an agentic system from an existing project, when studying a project's organizational DNA for cross-pollination, or when creating a skill/agent/team library inspired by a reference implementation.
Lean Ctx
100AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。