graph
Run the full OpenTrace knowledge-graph pipeline over a folder or repo — index, clustering, highlight surfacing, and the markdown…
Explore code structure, architecture, files, directories, and component relationships using the OpenTrace knowledge graph. Use this skill for ANY question about the codebase that the graph might answer — including browsing, searching, and understanding code organization.
$ npx -y skills add opentrace/opentrace --skill explore-code --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/explore-codeContext preview
The summary Claude sees to decide when to auto-load this skill.
Explore code structure, architecture, files, directories, and component relationships using the OpenTrace knowledge graph. Use this skill for ANY question about the codebase that the graph might answer — including browsing, searching, and understanding code organization.
name: explore-code description: | Explore code structure, architecture, files, directories, and component relationships using the OpenTrace knowledge graph. Use this skill for ANY question about the codebase that the graph might answer — including browsing, searching, and understanding code organization. Triggers on: - Structure: "how does X work", "what calls X", "show me the architecture", "where is X defined" - Browsing: "what's in X", "show me X", "look at X", "list the files in X", "what directories are there" - Discovery: "find X", "what examples exist", "what services/classes/files are there" - Exploration: "walk me through X", "give me an overview", "help me understand X" - General: any question about repo structure, code organization, or component relationships allowed-tools: mcp__opentrace_oss__search_graph, mcp__opentrace_oss__get_node, mcp__opentrace_oss__traverse_graph, mcp__opentrace_oss__list_nodes, mcp__opentrace_oss__get_stats, Read, Grep, Glob
The user wants to explore or understand something about the codebase. Use the OpenTrace knowledge graph to answer their question.
$ARGUMENTS
Use the OpenTrace MCP tools to investigate. Follow this approach:
1. **Orient** — Call `get_stats` to see what's indexed (node types and counts). This tells you what's available in the graph.
2. **Search** — Use `search_graph` to find nodes matching the user's query. Use `nodeTypes` to filter when appropriate:
3. **Inspect** — Use `get_node` on the best matches to see full details and neighbors.
4. **Trace** — Use `traverse_graph` to follow relationships:
5. **List** — Use `list_nodes` when the user wants to see all items of a type (e.g. all services, all files in a directory).
6. **Read source** — If nodes have a `path` property and the user needs code details, use `Read` to show the source.
A knowledge graph that maps your codebase structure, service architecture, and system relationships — then exposes it all through MCP so AI tools can understand your systems. Index any repo, any size, in seconds.
Run the full OpenTrace knowledge-graph pipeline over a folder or repo — index, clustering, highlight surfacing, and the markdown…