后端与数据库

database-documentation

a-tokyo/agent-skills

Generate grounded-and-verified, engine-agnostic database documentation that reaches 100% parity with the real schema. Introspects the LIVE database as ground truth and cross-validates it against ORM models, migrations, generated types, seeds, and application queries, then proves completeness by diffing the docs back against the database. Produces ER diagrams (mermaid), per-table data dictionaries, and a machine-readable schema.json. Works with PostgreSQL, MySQL, SQL Server, and SQLite across any ORM (Prisma, TypeORM, Drizzle, Sequelize, Knex, Django, Rails) or raw SQL. Use when asked to document a database, produce an ERD or data dictionary, write db/schema docs, audit schema drift, or refresh existing DB docs.

541 次安装
17 星标
收录于 2026.06.29

安装命令

$ npx skills add https://github.com/a-tokyo/agent-skills --skill database-documentation

SKILL.md

database-documentation

Document a database so completely and accurately that the docs are provably the schema, not a plausible guess at it. A half-correct schema doc is worse than none: people trust it and write broken code.

The one principle: grounded AND verified

Every statement in the output must be:

grounded — traceable to a concrete source, preferring the live database (introspection of the system catalog). ORM models, migrations, generated types, and seeds are claims about the database, not the database; the catalog is what actually runs.
verified — confirmed by re-introspecting the live database and diffing it against the generated docs until the diff is empty or every remaining difference is explicitly justified. Never write "documentation is complete" — instead make the diff empty and show it.

A frontier model left to itself reads the ORM, writes confident prose, and ships an incomplete and partly hallucinated schema (missed check-constraint enums, wrong ON DELETE, omitted legacy tables, invented columns). This skill exists to defeat exactly that. Two mechanisms do it: (1) the live DB is the oracle, and (2) judgment is never one agent's call — independent adversaries hunt for what one pass misses.