About this skill

Problem

Source code, API docs, SQL scripts, and configuration files often describe overlapping system behavior, but manual mapping of their relationships is slow and error-prone. graphify-data turns these text assets into a structured knowledge graph, making key entities and relationships easier to inspect, query, and hand off to downstream tooling.

How It Works

The skill accepts a project path, document paths, SQL files, and configuration files as input, then parses code, docs, SQL, and configs into a knowledge graph. It can emit JSON/GraphML graph data and an HTML visualization report. The workflow is batch-oriented and local-first: prepare inputs, run a sample pass, validate fields and output format, then process the full set. Execution focuses on single-item failures without aborting the whole batch, with a summary, skipped count, and failure details for targeted reruns.

Boundaries

Best suited for standard-format files, field extraction, structured output, and graph visualization.
Does not guarantee results for encrypted, corrupted, or non-standard files.
Treat output as a working reference and spot-check critical fields manually.

Screenshots

Use Cases

Map legacy code modules, API docs, and SQL dependencies into a graph during onboarding.
Compare config files against source code entities when validating consistency.
Extract tables, fields, and descriptions from SQL and docs into JSON graph data.
Review key docs, SQL, and config relationships in an HTML report before delivery.

Best For

Backend engineers taking over legacy systems who need to trace code, docs, and SQL relationships.
Data engineers maintaining pipelines who need SQL scripts structured into a graph.
Tech leads reviewing delivery docs who need to check config, docs, and code consistency.
Platform engineers building internal knowledge retrieval who need JSON/GraphML exports.