Stats
Actions
Tags
From rosetta
Documents the database layer of a project — schema, tables, entities, relationships, ORM models. Migrations are covered separately by /rosetta:doc-migrations. Use when the user says "document the database schema", "document the tables", "document the data model", "write docs for the entities", or similar. Runs the write-docs engine with a db-specific playbook, and asks the user at the start whether to run inline or in background.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rosetta:doc-dbThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Documents the database layer — schema, tables, entities, relationships, ORM models. A thin preset on top of `write-docs`, pre-framed for db topics and loaded with a db-specific playbook. Migrations are a separate concern — use `/rosetta:doc-migrations` for those.
Documents the database layer — schema, tables, entities, relationships, ORM models. A thin preset on top of write-docs, pre-framed for db topics and loaded with a db-specific playbook. Migrations are a separate concern — use /rosetta:doc-migrations for those.
Pre-framed topic: "database layer of this project — schema, entities, relationships, and the ORM patterns".
Playbook to read: ${CLAUDE_SKILL_DIR}/../write-docs/references/db.md.
Run the same rosetta-docs/ check as write-docs Step 1. If missing, redirect to /rosetta:init-docs and stop.
Prompt the user once, verbatim:
Should I run inline or in background?
- inline (default): I'll work step-by-step and pause to ask you which tables are load-bearing, whether to include indexes, and other scope questions. You'll see the draft before I write.
- background: I'll make best-judgment decisions and document what looks central, without pausing.
(Type
inline/background, or press enter for inline.)
Record the answer. It drives Step 4.
Read ${CLAUDE_SKILL_DIR}/../write-docs/references/db.md. Then follow write-docs Step 2–4 (package manager detection + rules + schema).
inline: continue with write-docs Step 5 through Step 12. Use Markdown tables for columns; skip <ApiRef> (it's for HTTP endpoints, not tables, per db.md). Ask the user which tables matter most before exhaustively listing.
background: compose a self-contained prompt that embeds this skill's workflow, the db playbook, and the user's pre-framed topic plus $ARGUMENTS as extra context. Dispatch via a forked subagent or a backgrounded claude -p through Bash. Return the identifier, then stop.
Use write-docs's Step 12 report format. Cite the db.md playbook sections that shaped non-obvious choices ("per db.md: scoped to 6 load-bearing tables instead of all 34").
<ApiRef> for tables.Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub marincervinschi/rosetta-plugin --plugin rosetta