Skills Guide

Database Schema Extraction and ERD Inference

VerifiedCaution

Connects to MySQL, MSSQL, and Oracle databases to extract schema metadata and infer table relationships using FK constraints, naming patterns (_id, _cd, _code, _no), and column matching. Exports the inferred schema as DBML or Mermaid ERD diagrams, useful for reverse-engineering legacy databases or documenting existing data models.

Download and use
Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#database#erd#schema#python#mysql

Recommended for

Backend developerClaude CodeCode reviewFrontend developerFullstack developerRefactoring

Automated summary

A Python worker that extracts metadata from a database, infers relationships between tables, and exports ERD diagrams in DBML or Mermaid format.

Strengths

  • Supports MySQL, MSSQL, and Oracle via dedicated connectors
  • Relationship inference using foreign keys, naming conventions, and comments
  • Export to DBML and Mermaid for immediate visualization
  • Clean REST API with 7 well-defined endpoints

Limitations

  • Only MySQL has been tested in real conditions
  • No unit or integration tests implemented
  • Performance on large schemas (200+ tables) has not been validated
When to use it

When you need to quickly analyze a database structure and generate an ERD diagram for documentation or refactoring.

When not to use it

For databases with complex semantic relationships not expressed by foreign keys or standard naming (e.g., implicit dependencies in JSON columns).

Security analysis

Caution
Quality score80/100

The SKILL.md is a project documentation file describing a backend worker that starts a web service and interacts with databases. While not inherently destructive, automated execution of a server could expose internal resources and database access without proper authentication checks, warranting caution.

Findings
  • •Skill describes starting a FastAPI server on port 8000, which could expose internal services if run automatically by an AI agent.
  • •Connects to production databases (MySQL, MSSQL, Oracle) using potentially stored credentials, increasing risk if mishandled.
  • •No explicit dangerous commands, but running an unhardened server introduces network surfaces.
How this analysis is made

Examples

Extract metadata from a MySQL database
Connect to my MySQL database at localhost:3306, schema 'sales', and extract all table metadata including columns, types, comments, and primary keys.
Infer relationships and generate ERD diagram
From the extracted metadata of the 'sales' database, infer all relationships (foreign keys, _id patterns, etc.) and build an ERD graph, then export it as Mermaid code.
Test database connection and export DBML
Test connection to my MySQL database 'inventory', then extract its schema, infer relations, and export the ERD as DBML.

ERDAI DB/ERD Skill (Python Worker)

참조 문서

  • agent/db-connection.md
  • agent/erd-engine.md
  • agent/backend.md

현재 구현 상태

✅ 완료

| 항목 | 파일 | |---|---| | FastAPI 앱 구조 | app/main.py | | 전체 7개 엔드포인트 | app/routers/worker.py | | MySQL 커넥터 | app/services/connectors/mysql_connector.py | | MSSQL 커넥터 (pymssql) | app/services/connectors/mssql_connector.py | | Oracle 커넥터 (oracledb) | app/services/connectors/oracle_connector.py | | 커넥터 팩토리 | app/services/connectors/factory.py | | 메타데이터 추출 서비스 | app/services/metadata_service.py | | 관계 추론 서비스 | app/services/inference_service.py | | DBML/Mermaid export | app/services/export_service.py | | Pydantic 모델 | app/models/connection.py, metadata.py, erd.py | | requirements.txt | pymysql/pymssql/oracledb/pydantic>=2.10.0 |

엔드포인트 목록

GET  /worker/health
POST /worker/test-connection       # TestConnectionRequest → TestConnectionResponse
POST /worker/extract-metadata      # ExtractMetadataRequest → SchemaMetadata
POST /worker/infer-relations       # InferRelationsRequest → list[InferredRelation]
POST /worker/build-erd             # BuildErdRequest → ErdGraph
POST /worker/export/dbml           # BuildErdRequest → PlainText
POST /worker/export/mermaid        # BuildErdRequest → PlainText

관계 추론 로직 (inference_service.py)

  1. 실제 FK — fk_refs에서 confidence=FK (score=1.0)
  2. _id 패턴 — 테이블명 매칭 시 HIGH (0.8~0.9), 코멘트 일치 +0.1
  3. _cd/_code 패턴 — MEDIUM (0.6~0.7)
  4. _no 패턴 — LOW (0.45~0.55)
  5. PK 컬럼명 직접 일치 — MEDIUM (0.55)

❌ 남은 작업

  1. MSSQL/Oracle 실제 연결 테스트 — MySQL만 검증됨
  2. 도메인 자동 분류 — 테이블 prefix 기반 (예: mail_ → MAIL)
    • 현재 Worker에서 domain 필드 반환하지 않음 (erdBuilder에서 'ETC' 기본값)
    • inference_service.py 또는 build-erd 엔드포인트에서 prefix 분류 추가 필요
  3. 대형 스키마 성능 — 200+ 테이블 처리 시 타임아웃 테스트
  4. pytest 테스트 — tests/ 디렉터리 없음

기동 방법

cd worker
python -m uvicorn app.main:app --port 8000 --reload
# python main.py 로 실행 금지 (모듈 경로 문제)

Python 버전 주의

  • Python 3.14 이상: pydantic>=2.10.0 필수 (cp314 wheel 있음)
  • pydantic 2.9.x: Rust build 필요 → 설치 실패

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/database-schema-extraction-and-erd-inference-mm5t89p1/download' --output '.skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1/SKILL.md.part' && mv '.skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1/SKILL.md.part' '.skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/database-schema-extraction-and-erd-inference-mm5t89p1/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

React Hook Form Best Practices

Development

Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.

Claude CodeCursorWindsurf+2intermediateSafe 108,623
Skills Guide Bot

Emotion to Mantine Migration

Development

Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.

Claude CodeCursorWindsurf+1intermediateSafe 48,981
Skills Guide Bot

Scope Creep Detector

Development

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.

Claude CodeCursorCodexintermediateSafe 135,015
Skills Guide Bot