explain
/explain
Explain a database schema, model, or a single finding in plain language, with a paradigm-aware diagram — what the tables/collections/keyspaces are, how they relate, and where the data lives. Read-only; teaches, does not change anything. Use when the user asks to explain, describe, walk through, draw, or diagram a schema, a data model, a relationship, or what a specific audit finding means.
- Author
- hainrixz ↗
- Repository
- claude-db ↗
- Licence
- MIT
- Last repository change
- 25.10.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 1
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- SKILL.md zawiera komentarze HTML (1). Nie widać ich w podglądzie Markdown, a model je czyta.
What it does and when to use it
Explain a database schema, model, or a single finding in plain language, with a paradigm-aware diagram — what the tables/collections/keyspaces are, how they relate, and where the data lives. Read-only; teaches, does not change anything. Use when the user asks to explain, describe, walk through, draw, or diagram a schema, a data model, a relationship, or what a specific audit finding means.
Arguments
/explain <path|table|finding-id> | --query \"<SQL>\" | <paste an EXPLAIN plan> [--depth overview|detailed] [--lang en|es]
Original author description
Explain a database schema, model, or a single finding in plain language, with a paradigm-aware diagram — what the tables/collections/keyspaces are, how they relate, and where the data lives. Read-only; teaches, does not change anything. Use when the user asks to explain, describe, walk through, draw, or diagram a schema, a data model, a relationship, or what a specific audit finding means.
How it works
- What to do
- Query / EXPLAIN-plan mode
- Honesty
SKILL.md preview
---
name: explain
description: Explain a database schema, model, or a single finding in plain language, with a paradigm-aware diagram — what the tables/collections/keyspaces are, how they relate, and where the data lives. Read-only; teaches, does not change anything. Use when the user asks to explain, describe, walk through, draw, or diagram a schema, a data model, a relationship, or what a specific audit finding means.
argument-hint: "<path|table|finding-id> | --query \"<SQL>\" | <paste an EXPLAIN plan> [--depth overview|detailed] [--lang en|es]"
allowed-tools: Read, Grep, Glob, Bash
---
<!-- Copyright (c) 2026 Enrique Rocha (@soyenriquerocha) · tododeia.com · id er-f37b7121 -->
# /claude-db:explain
Plain-language description of a schema (or one finding), plus a **paradigm-aware diagram**. Read-only — explains, never edits or migrates.
`$ARGUMENTS` = `<path|table|finding-id> [flags]`. The target can be a schema/ORM/migration path, a single table/collection name, or a finding `id` from a prior audit.
## What to do
1. Detect the paradigm/engine (`scripts/detect-stack.mjs`) and parse the model (`scripts/parse-schema.mjs` / `parse-orm-python.py`).
2. Give a **plain-language description first** — no jargon in the opening: what each entity holds, who owns what, and how the pieces connect, in the user's words ("a user has many orders; each order belongs to exactly one user").
3. Render a **paradigm-aware diagram** (Mermaid) with `node scripts/gen-diagram.mjs --file <schema> [--paradigm relational|document|key-value|wide-column|graph]` — paradigm-aware: ERD for relational, access-pattern map for document, key+GSI sketch for DynamoDB/KV, node/edge for graph:
- **Relational** → `erDiagram` with tables, PKs/FKs, and cardinality.
- **Document** → embedding/reference tree showing what is nested vs referenced.
- **Key-value** → access-pattern / key-design sketch (partition + sort key).
- **Wide-column** → table-per-query / partition-key layout.
- **Vector** → collection + metric/dimension + metadata filter fields.
- **Time-series** → hypertable / measurement + tags + retention.
- **Graph** → node-and-edge sketch with relationship types.
4. Offer an **expandable technical layer** below the plain description: exact column types, index definitions, constraint names, on-delete behavior — for the reader who wants the precise DDL.
5. If the target is a **finding id**, explain what it checks, which score/axis it affects (design | performance | both), why it matters, and how to reproduce it (`verification.reproduce`).
## Query / EXPLAIN-plan mode
Two additional inputs, both reusing the **db-query-patterns (M13)** reasoning:
- **`--query "<SQL>"`** — given a raw SQL statement, explain in plain language *why it would be slow* and *what fixes it*: detect M13 shapes (SELECT *, structural N+1, OFFSET deep paging, non-SARGable predicates), then recommend the concrete index, keyset rewrite, or predicate change that lets an index be used. This is static reasoning over the query text — no live DB needed.
- **paste-an-EXPLAIN-plan** — given a pasted `EXPLAIN`/`EXPLAIN ANALYZE` plan, read the plan nodes (seq scans, sort/hash spills, row estimate vs actual, nested-loop blowups) and explain which step dominates and what index/rewrite removes it, again via the M13 reasoning.
- If the user wants a **live plan generated** for them (running `EXPLAIN` against their database) rather than pasting one, mark the request **`needs_api` / Tier-2** and do not fabricate plan numbers — explain statically from the query text instead, or ask them to paste the plan.
## Honesty
- Describe only what is actually in the model. Never invent columns, relationships, row counts, or latency. If a relationship is implied but not enforced (e.g. a logical FK with no constraint), say so explicitly.
- Respond in the user's language (EN/ES); `--lang` overrides.
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · hainrixz/claude-db | 90 | MIT |
| crbnos/carbon | 100 | AGPL-3.0 |
| PerilloAI/flowtrace-plugin | 100 | Apache-2.0 |
| mickeyyaya/evolve-loop | 100 | Apache-2.0 |
| zenobi-us/dotfiles | 100 | MIT |
| imgly/agent-skills | 100 | MIT |
| marcel-bich/marcel-bich-claude-marketplace | 100 | MIT |
| nicodiansk/draw-it-out | 100 | MIT |
| ramboz/jig | 100 | MIT |
Database snapshot: 13.11.2026 · package version 19e66588a922 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100create-data-model
Design a data model from feature requirements when the user asks to create a schema, design database tables, model entities, plan a data layer, or create an ERD - 100flux-schema
Design and build database schema — tables, columns, types, indexes, constraints, relationships. Given a domain description, output the schema and write the files. Use when asked to "design schema", "database design", "create tables", or "data model". - 90st-explain
Explain how a piece of code works, why it is built that way, and what that means, in plain language a person can follow. Use for 'how does X work', 'why is it like this', 'teach me this', onboarding to a subsystem, or /st-explain. - 100html-erd-explorer
Generate HTML entity-relationship diagrams (ERDs) and database schema visualizations with clickable tables, relationship paths, and migration before/after views. Use whenever the user has a database schema, data model, or table structure to document, explain, migrate, or explore… - 90ds-explain
Explain how a piece of code works, why it is built that way, and what that means, in plain language a person can follow. Use for 'how does X work', 'why is it like this', 'teach me this', onboarding to a subsystem, or /ds-explain. - 100schema-designer
Design database schemas with proper normalization, relationships, constraints, and indexes. Use when creating database tables, modeling data relationships, or designing database structure.