Skill Claude CodeCodex
Review code changes in Memgraph's storage layer, including MVCC, concurrency patterns, WAL, recovery, DDL operations, index/constraint management, delta chains, and skip list operations. Invoke for pull requests or changes to src/storage/v2/.
Plugin Claude Code
Runtime plugins for Agent Context Graph.
Instructions file CodexOpenCode
Instructions for memgraph/ai-toolkit, covering agents.md, what this repo is, repository layout, the context graph family (context-graph/) and environment & setup.
Plugin Claude Code
Capture Claude Code runtime activity through Agent Context Graph hooks.
Hook
Runs when a session starts, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when you submit a prompt, before the agent sees it, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs to expand your prompt before the agent sees it, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs before the agent uses a tool, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs after a tool call finishes, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when a tool call fails, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when the agent asks permission for an action, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs on the PermissionDenied event, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when a subagent starts, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when a subagent finishes, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs when the agent finishes a response, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Hook
Runs on the StopFailure event, running agent-context-graph hook run claude-code --connector skills-. From memgraph/ai-toolkit.
Skill Claude CodeCodex
Set up and check Claude Code context capture into Memgraph.
Skill Claude CodeCodex
Used to release all toolbox, integrations, agents. Use when releasing a subproject to PyPI, Docker Hub, or when the user asks to release or publish.
Plugin Claude Code
Skills for the Memgraph graph database: Cypher, data modeling, indexes, algorithms, query modules, and GraphRAG.
Skill Claude CodeCodex
Generate apps, demos, dashboards, diagrams, landing pages, and any visual output that looks like it belongs in the Memgraph product family. Use whenever producing UI, visual artifacts (Mermaid, SVGs, charts), Lab-style admin tools, internal dashboards, feature splash pages, or embeddable widgets for Memgraph engineers.
Skill Claude CodeCodex
Develop custom query modules in C++ for Memgraph graph database. Use when creating high-performance graph algorithms, procedures (ProcedureType::Read/Write), or functions using the mgp.hpp C++ API. Covers compilation, memory management, graph traversal, and module deployment.
Skill Claude CodeCodex
Write Cypher queries for Memgraph, including Memgraph-specific extensions like deep path traversals (BFS, DFS, WSP, ASP, KSP with filter/weight lambdas), text and vector search, parallel execution, and CALL subqueries. Use when the user asks to write, fix, or optimize a Cypher query for Memgraph, or asks about Cypher…
Skill Claude CodeCodex
Configure Memgraph triggers, transactions, storage modes, data durability, and memory settings. Use when the user asks about triggers, transaction isolation levels, storage modes (transactional vs analytical), snapshots, WAL, memory limits, data types, or database runtime configuration.
Skill Claude CodeCodex
Language-agnostic blueprint for building GraphRAG systems with Memgraph and agent tooling. Covers end-to-end architecture, schema design, ingestion, hybrid retrieval, tool contracts, and evaluation. Use when designing GraphRAG platforms that must work across multiple programming languages.