菜单
Explore a graph or network dataset — structure, statistics, paths, and visualization. Use when working with DOT, GML, GraphML, or Mermaid files.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Analyze an A/B test experiment and provide a clear ship/iterate/no-ship recommendation. Use when evaluating experiment results.
Run correlation analysis on connected data, identify strong relationships, and suggest regression models. Use when exploring relationships between variables.
Discover natural groupings in data using clustering algorithms with evaluation and visualization. Use when segmenting data or finding patterns.
Run an end-to-end data analysis pipeline — connect, profile, analyze, and report. Use when performing a complete analysis workflow.
Connect to a data source, profile its schema and quality, and recommend appropriate analyses. Use when starting work with a new dataset.
Analyze a time series and generate forecasts with confidence intervals. Use when predicting future values from historical data.
| name | graph-explore |
| description | Explore a graph or network dataset — structure, statistics, paths, and visualization. Use when working with DOT, GML, GraphML, or Mermaid files. |
| allowed-tools | mcp__localdata__connect_database mcp__localdata__get_graph_stats mcp__localdata__get_edges mcp__localdata__get_neighbors mcp__localdata__get_node mcp__localdata__find_path mcp__localdata__export_graph |
| argument-hint | <file-path> |
Connect to a graph file, analyze its structure and key nodes, find paths, and export visualizations.
Connect to the graph. Call connect_database with the file path from $ARGUMENTS. The tool auto-detects graph formats including DOT, GML, GraphML, and Mermaid. Note the assigned database name.
Get graph statistics. Call get_graph_stats with the database name. Review: node count, edge count, density, whether the graph is directed or undirected, connected components count, and average degree. This gives an overview of the graph's scale and connectivity.
Identify hub nodes. From the stats, note nodes with the highest degree (most connections). Call get_neighbors for the top 3 highest-degree nodes to understand what they connect to. These hubs are often the most important entities in the network.
Explore structure. Call get_edges to retrieve a sample of edges. Look for patterns: are edges weighted? Do they have labels or types? Is the graph sparse or dense? Identify any isolated components or bridges.
Inspect specific nodes. For nodes of interest (hubs or user-specified), call get_node to retrieve node attributes and metadata. Note any labels, types, or properties that provide context.
Find paths. If there are at least two notable nodes, call find_path between them. Review the shortest path length and the intermediate nodes. This reveals how information or relationships flow through the network.
Export a visualization. Call export_graph with a suitable format (DOT for Graphviz rendering, or the original format for round-tripping). For large graphs, suggest filtering to a subgraph around nodes of interest before exporting.
Summarize findings. Present:
