Database Schema Documenter skill for Claude and Codex
Produces a data dictionary for an existing database that analysts and new engineers can read: purpose per table, every column with type and meaning, keys and…
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
Use when an existing database needs a data dictionary with table purposes, column meanings, keys, relationships, and indexes for engineers or analysts. Do not use for designing a new schema, generating DDL, reformatting raw definitions into tables, or validating a schema against best practice. Related topics: coding, database.
What it will ask you for
- Database platform (choose one: MySQL, PostgreSQL, Oracle, SQL Server, SQLite, MariaDB)
- Tables definition (longer free text)
- Include indexes (choose one: Yes, No)
- Include foreign key relationships (choose one: Yes, No)
- Output format (choose one: Markdown, HTML, PDF outline)
- Diagram style (choose one: ERD, UML, None)
- Primary audience (choose one: Backend engineers, Data analysts, Both)
How it works
- Group tables by domain in an overview and describe how a typical record flows through them.
- Write each table's purpose and a columns table with type, nullability, default, and meaning, marking inferred meanings.
- List primary keys, foreign keys with relationship direction when requested, and indexes with the query pattern each serves when requested.
- Add the audience section: Common joins for analysts, Constraints and invariants for engineers, or both.
- Insert the diagram placeholder when a style is chosen and assemble the document with a title, contents, and consistent headings in the selected format.
What you get
One document in the selected format: title, table of contents, overview by domain, a section per table (purpose, columns table, keys, relationships, indexes), the audience section, and a diagram placeholder when requested.
What it watches out for
- Listing columns without meanings, which turns the document into a copy of the DDL nobody reads.
- Describing indexes without the query they serve, so analysts still guess which filters are fast.
- Omitting the overview, so a reader has to reverse-engineer the domain from table names.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.