Generated banner for Schema Exploration
Generated logo for Schema Exploration

Schema Exploration

Timescale (TigerData)OfficialCreated by tigerdataDistributed by Timescale (TigerData)

  • Skill
  • Tool integration
  • Data and AI
  • Apache-2.0
  • No issues found

From the author

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.
— the description by tigerdata

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a systematic approach for AI agents to investigate unfamiliar PostgreSQL databases. It emphasizes read-only catalog exploration to understand schema structure, business concepts, and object relationships. By prioritizing metadata analysis over direct data inspection, it ensures safe, authorized, and context-aware interactions with database environments, requiring explicit user approval before accessing data-derived statistics or row samples.

What it does

  • Inventory database schemas, tables, views, and routines using read-only catalog queries.
  • Corroborate business meaning through comments, keys, and dependency analysis.
  • Request and manage user approval for accessing data-derived statistics or row samples.
  • Validate query plans using EXPLAIN without executing data-modifying operations.
  • Identify objects owned by installed PostgreSQL extensions.
  • Report findings while clearly distinguishing between observed facts and inferences.

When to use it

  • When you need to write SQL for an unfamiliar database schema.
  • When a user asks for data-backed answers like counts or recent changes.
  • When you need to locate where specific business concepts reside in the database.
  • When you need to understand how specific tables, views, triggers, or RLS policies function.

Advantages

  • Minimizes risk by defaulting to read-only metadata exploration.
  • Prevents unauthorized data exposure by requiring explicit approval for statistics and row samples.
  • Provides a clear, repeatable process for mapping database structure to business logic.
  • Reduces errors in query generation by validating join keys and grains first.
  • Ensures transparency by reporting limitations and distinguishing observations from assumptions.

Usage examples

“How many active users are in the database?”
The agent will first identify the relevant user table, check its schema and constraints, and then request approval to query statistics or sample rows to provide an accurate count.
“Where is the order history stored?”
The agent will search the catalog for tables or views related to 'orders' or 'history', inspect their columns and foreign keys, and report the likely location with supporting evidence.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/timescale/schema-exploration/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip schema-exploration.zip -d .agents/skills

Documentation by tigerdata

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

  1. Establish the current database, server version, role, and scope. Use overview for a small inventory. Choose relevant schemas; do not assume public contains the application.

  2. 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.

  3. 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.

  4. If the user wants SQL, follow query authoring: establish join keys and grain, then validate a vetted read-only query with plain EXPLAIN where authorized. Do not mistake a valid plan for proof of business semantics.

  5. 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).

Example finding

Illustrative only; report facts verified in the target database:

  • Observed: sales.orders has a primary key on order_id and a foreign key from account_id to sales.accounts.account_id.

  • Inferred: sales.orders likely records one row per order; the keys support this, but do not establish what the business calls an “order.”

  • Unresolved: The catalog does not show whether canceled orders remain in this table. Confirm with the application owner before assuming they do.

Safety and execution

  • Prefer structural catalog queries; pg_stats is data-derived and requires approval too. Do not change schema, data, roles, or session-wide settings without authorization. Never call discovered functions or procedures, refresh materialized views, or run EXPLAIN ANALYZE on unknown queries. A function marked STABLE or IMMUTABLE is not a safety guarantee.

  • If your client supports transactions, use a read-only transaction and a reasonable statement timeout for exploration. Metadata queries are not a license to run full-table counts or unrestricted scans. Ask before sampling data; sample only when necessary, with explicit limits and a clear understanding of table size and access controls.

  • All reference queries are plain PostgreSQL SQL. Bind $1, $2, etc. as values using your client's API. psql users can follow the optional psql adapter. Never interpolate an untrusted object name as raw SQL; placeholders cannot replace SQL identifiers in data queries.

  • Queries target PostgreSQL 18. Each version-sensitive section notes alternatives for older majors where applicable. Check server_version_num first. If a query fails due to permissions or version differences, report the limitation instead of guessing.

Files

references/overview.md

Overview: find the relevant schema and object

Contents

  • Context

  • Schema inventory

  • Relations in one schema

  • Routines in one schema

  • User-defined triggers in one schema

Run the context query first. Do not inventory every object in a large database: start with schema counts, then restrict later queries to a chosen schema. Counts include extension-owned objects; consult extensions if they dominate the inventory. Queries target PostgreSQL 18 and use catalog columns also present in PostgreSQL 14–17.

Context

No parameters.

select
  current_database() as database_name
, current_user as role_name
, current_setting('server_version_num')::integer as server_version_num
, current_setting('search_path') as search_path
, current_setting('transaction_read_only') as transaction_read_only
;

Schema inventory

No parameters. Counts describe catalog objects, not only objects usable by the current role. tables counts ordinary and partitioned tables (including partition children); foreign_tables is separate because its data is accessed through a foreign server. Excludes built-in and temporary schemas; extension schemas may still appear.

select
  n.nspname as schema_name
, pg_catalog.has_schema_privilege(n.oid, 'USAGE') as current_role_has_schema_usage
, pg_catalog.obj_description(n.oid, 'pg_namespace') as comment
, count(c.oid) filter (where c.relkind in ('r', 'p')) as tables
, count(c.oid) filter (where c.relkind = 'f') as foreign_tables
, count(c.oid) filter (where c.relkind in ('v', 'm')) as views
, count(c.oid) filter (where c.relkind = 'S') as sequences
, (select count(*) from pg_catalog.pg_proc p where p.pronamespace = n.oid and p.prokind in ('f', 'p')) as routines
, ( select count(*)
    from pg_catalog.pg_trigger t
    join pg_catalog.pg_class tc on tc.oid = t.tgrelid
    where tc.relnamespace = n.oid
      and not t.tgisinternal
  ) as user_triggers
from pg_catalog.pg_namespace n
left join pg_catalog.pg_class c on c.relnamespace = n.oid
where n.nspname not in ('pg_catalog', 'information_schema', 'pg_toast')
  and n.nspname !~ '^pg_(temp|toast_temp)_'
group by n.oid, n.nspname
order by n.nspname
;

Relations in one schema

$1 = schema name. reltuples is a possibly stale estimate, not an exact row count; partitioned parents can show misleading sizes. relispopulated applies to materialized views. Privilege columns are current-role signals, not guarantees of access: schema usage, column grants, RLS, and underlying view objects may also matter.

select
  c.oid
, c.relname as object_name
, pg_catalog.pg_get_userbyid(c.relowner) as owner
, pg_catalog.has_schema_privilege(n.oid, 'USAGE') as current_role_has_schema_usage
, pg_catalog.has_table_privilege(c.oid, 'SELECT') as current_role_has_table_select
, case c.relkind
    when 'r' then 'table'
    when 'p' then 'partitioned table'
    when 'f' then 'foreign table'
    when 'v' then 'view'
    when 'm' then 'materialized view'
  end as kind
, c.reltuples::bigint as estimated_rows
, c.relrowsecurity as rls_enabled
, c.relispopulated as populated
, pg_catalog.obj_description(c.oid, 'pg_class') as comment
from pg_catalog.pg_class c
join pg_catalog.pg_namespace n on n.oid = c.relnamespace
where n.nspname = $1 -- $1 = schema name
  and c.relkind in ('r', 'p', 'f', 'v', 'm')
order by c.relname
;

Use tables for a local table, foreign tables for relkind = 'f', views for a view or materialized view, and security if RLS or visibility is relevant. Partition children may be listed as ordinary tables; inspect inheritance before counting them as independent business entities.

Routines in one schema

$1 = schema name. Signatures distinguish overloads; aggregates and window functions are omitted. Privilege columns reflect the current role, but do not guarantee a call will succeed. Inspect only relevant routines using routines.

select
  p.oid
, p.proname as routine_name
, pg_catalog.pg_get_userbyid(p.proowner) as owner
, pg_catalog.has_schema_privilege(n.oid, 'USAGE') as current_role_has_schema_usage
, pg_catalog.has_function_privilege(p.oid, 'EXECUTE') as current_role_has_execute
, case p.prokind when 'p' then 'procedure' else 'function' end as kind
, pg_catalog.pg_get_function_identity_arguments(p.oid) as identity_arguments
, pg_catalog.obj_description(p.oid, 'pg_proc') as comment
from pg_catalog.pg_proc p
join pg_catalog.pg_namespace n on n.oid = p.pronamespace
where n.nspname = $1 -- $1 = schema name
  and p.prokind in ('f', 'p')
order by p.proname, identity_arguments
;

User-defined triggers in one schema

$1 = schema containing the relation on which the trigger is defined (the trigger function may be in another schema). Excludes internal triggers created by PostgreSQL, notably those enforcing foreign keys. Includes disabled triggers and trigger clones on partitions; cloned_from_parent identifies those clones. A trigger's existence does not establish that it currently fires. Drill into a relevant relation with triggers for definitions, events, and firing behavior.

select
  c.relname as relation_name
, t.tgname as trigger_name
, t.tgenabled as enabled_mode
, t.tgparentid <> 0 as cloned_from_parent
, fn.nspname as function_schema
, p.proname as function_name
, pg_catalog.pg_get_function_identity_arguments(p.oid) as function_identity_arguments
from pg_catalog.pg_trigger t
join pg_catalog.pg_class c on c.oid = t.tgrelid
join pg_catalog.pg_namespace n on n.oid = c.relnamespace
join pg_catalog.pg_proc p on p.oid = t.tgfoid
join pg_catalog.pg_namespace fn on fn.oid = p.pronamespace
where n.nspname = $1
  and not t.tgisinternal
order by c.relname, t.tgname
;

Installed extensions often explain unfamiliar schemas and object names; see extensions.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
tigerdata
Publisher
Timescale (TigerData) (Official)
Distributed by
Timescale (TigerData)
Source
timescale/pg-aiguide · skills/schema-exploration · commit c39008a
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • NOTICE (added by AutoGineer from NOTICE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by tigerdata or Timescale (TigerData).

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download schema-exploration.zip