Agent skill
graph-export
[Code Intelligence] Export the code review knowledge graph to a JSON file. Dumps all nodes (functions, classes, files) and edges (calls, imports, inheritance) from graph.db for external analysis or inspection.
Install this agent skill to your Project
npx add-skill https://github.com/duc01226/EasyPlatform/tree/main/.claude/skills/graph-export
SKILL.md
Export Graph
Export the complete knowledge graph from .code-graph/graph.db to a readable JSON file.
Prerequisites
- Graph must be built first: run
/graph-buildif.code-graph/graph.dbdoesn't exist - Requires Python 3.10+ with tree-sitter, tree-sitter-language-pack, networkx
Steps
-
Export graph — Run via Bash:
bashpython .claude/scripts/code_graph export --jsonDefault output:
.code-graph/graph-export.json -
Export specific files only (optional):
bashpython .claude/scripts/code_graph export --files src/auth.py src/api.py --jsonThis exports only nodes and edges belonging to the specified files.
-
Custom output path (optional):
bashpython .claude/scripts/code_graph export -o custom-path.json --json -
Report results: File path, node count, edge count, file size.
Output Format
{
"version": "1.8.4-easyclaude",
"stats": { "total_nodes": N, "total_edges": N, "files_count": N, "languages": [...] },
"nodes": [
{ "kind": "Function", "name": "login", "qualified_name": "auth.py::login", "file_path": "...", "line_start": 10, "line_end": 25, "language": "python" }
],
"edges": [
{ "kind": "CALLS", "source": "api.py::handler", "target": "auth.py::login", "file_path": "...", "line": 15 }
]
}
Implicit Edges in Export
The exported JSON includes ALL edge types, including implicit connections:
MESSAGE_BUS— cross-service bus message producer-to-consumer linksTRIGGERS_EVENT— entity CRUD to event handler linksPRODUCES_EVENT— event handler to bus producer linksTRIGGERS_COMMAND_EVENT— command to command event handler linksAPI_ENDPOINT— frontend HTTP call to backend route links
These edges are created by the implicit connector and API connector during build/sync.
Use Cases
- Inspect graph contents for debugging
- Feed into external analysis tools
- Verify graph correctness after build
- Share graph snapshot with team members
Closing Reminders
- MUST break work into small todo tasks using
TaskCreateBEFORE starting - MUST search codebase for 3+ similar patterns before creating new code
- MUST cite
file:lineevidence for every claim (confidence >80% to act) - MUST add a final review todo task to verify work quality
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
fix-parallel
[Implementation] Analyze & fix issues with parallel fullstack-developer agents
ask
[Utilities] Answer technical and architectural questions.
claude-code
[Utilities] Claude Code CLI setup, configuration, troubleshooting, and feature guidance. Triggers on claude code setup, hook not firing, MCP connection, context limit, skill creation, slash command setup.
workflow-deployment
[Workflow] Trigger Deployment & Infrastructure workflow — CI/CD pipelines, Docker, Kubernetes setup and deployment.
workflow-idea-to-pbi
[Workflow] Trigger Idea to PBI workflow — po/ba workflow: capture idea, refine to pbi, create stories, prioritize.
easy-claude-help
[Utilities] Configuration guide for the easy-claude framework — explain settings, guide users through configuring .ck.json.
Didn't find tool you were looking for?