generating-database-documentation
About
This skill generates comprehensive database documentation including ERD diagrams, table relationships, and data dictionaries from existing schemas. It supports multiple database engines and produces interactive HTML documentation for team onboarding or architectural reviews. Use it when triggered by terms like "database documentation," "ERD diagram," or the `/db-docs` command.
Documentation
Overview
This skill empowers Claude to create detailed database documentation from existing database schemas. It leverages the database-documentation-gen plugin to automate the process, saving time and ensuring consistency. The generated documentation includes ERD diagrams, table relationships, and detailed information about database objects.
How It Works
- Activation: Claude recognizes the user's request for database documentation, ERD diagrams, or a data dictionary, triggering the database-documentation-gen plugin.
- Schema Analysis: The plugin connects to the specified database and analyzes its schema, extracting information about tables, columns, relationships, indexes, triggers, and stored procedures.
- Documentation Generation: The plugin generates comprehensive documentation in various formats, including ERD diagrams, data dictionaries, and interactive HTML documentation.
When to Use This Skill
This skill activates when you need to:
- Generate documentation for a new or existing database.
- Create ERD diagrams for architectural reviews.
- Produce a data dictionary for data governance purposes.
- Onboard new team members to a database project.
Examples
Example 1: Documenting an Existing Database
User request: "Generate database documentation for the 'users' database."
The skill will:
- Activate the database-documentation-gen plugin.
- Connect to the 'users' database and analyze its schema.
- Generate comprehensive documentation, including ERD diagrams and a data dictionary.
Example 2: Creating an ERD Diagram
User request: "Create an ERD diagram for the 'orders' database."
The skill will:
- Activate the database-documentation-gen plugin.
- Connect to the 'orders' database and analyze its schema.
- Generate an ERD diagram illustrating the relationships between tables in the 'orders' database.
Best Practices
- Database Credentials: Ensure Claude has the necessary database credentials to access the database schema.
- Database Selection: Clearly specify the database for which documentation should be generated.
- Output Format: Consider specifying the desired output format for the documentation (e.g., HTML, Markdown).
Integration
This skill can be integrated with other plugins to further enhance the documentation process. For example, it can be combined with a diagramming plugin to customize the ERD diagrams or with a document generation plugin to create more sophisticated documentation formats.
Quick Install
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/database-documentation-genCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.