Schema Exploration
Explore an existing PostgreSQL database before answering questions about its data or...
Install
npx skills add timescale/pg-aiguide --skill schema-exploration -g -a claude-code -y- Repository
- timescale/pg-aiguide1.9k
- Category
- Design
- Updated
- 8d ago
- License
- Apache-2.0
- Context cost
- Lightabout 934 tokens
- Runs scripts
- No, instructions only
What it does
Explore an existing PostgreSQL database before answering questions about its data or writing SQL. Use this skill whenever a user asks for a query or a data-backed answer against an unfamiliar schema (counts, missing or failed records, recent changes), asks where a business concept lives, or asks how tables, joins, views, routines, triggers, RLS, or extensions work. Find the relevant objects with read-only pg_catalog queries, then request approval before inspecting data-derived statistics or rows. Not a schema-design or migration guide.
Explore a PostgreSQL database
Start with the user's question, not a full-database audit unless that is the explicit ask. Use the database connection already available to you; if none is available, ask for access or work from provided schema files. Stay within the database and schemas the user has authorized. Catalog metadata can reveal sensitive names or source code: do not export it unnecessarily.
Workflow
- Establish the current database, server version, role, and scope. Use overview for a small inventory. Choose relevant schemas; do not assume
publiccontains the application. - Pick the most promising object(s) and read only the matching drill-down reference: tables, partitioning/inheritance, foreign tables, views, routines, triggers, security/RLS, or extensions. Follow cross-references only when the question requires them.
- Corroborate meaning with comments, definitions, keys, and known dependencies. Names are clues, not proof of business meaning. If data-derived values would help, use data-derived values only after obtaining approval for the specific columns and access method. Ask the user when semantics remain ambiguous.
- If the user wants SQL, follow query authoring: establish join keys and grain, then validate a vetted read-only query with plain
EXPLAINwhere authorized. Do not mistake a valid plan for proof of business semantics. - Stop once you can answer. Report the specific schema-qualified objects and evidence, distinguish observations from inferences, and state limitations (permissions, stale statistics, missing dependencies, unknown application logic).
