CtrlK
BlogDocsLog inGet started
Tessl Logo

alonso-skills/postgres

Comprehensive PostgreSQL reference for developers and DBAs covering versions 14–18. Use whenever the user asks about PostgreSQL syntax, DDL/DML/DQL, joins, LATERAL, CTEs, window functions, GROUPING SETS, DISTINCT ON, RETURNING, ON CONFLICT, PL/pgSQL, functions, procedures, triggers, views, materialized views, indexes (B-tree/GIN/GiST/BRIN/Hash/Bloom), MVCC, VACUUM, autovacuum, WAL, TOAST, partitioning, replication (streaming/logical), backup, PITR, HA (Patroni/repmgr), pgBouncer, EXPLAIN ANALYZE, RLS, roles, extensions (pgvector, PostGIS, TimescaleDB, Citus, pg_trgm, pg_cron), JSON/JSONB, full-text search, UUID, timestamptz, COPY, system catalogs, collations, large objects, cursors, GUC, or any Postgres administration, performance, security, replication, backup, or recovery topic.

94

1.36x
Quality

94%

Does it follow best practices?

Impact

94%

1.36x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

87%

25%

PostgreSQL Row-Level Security Reference Guide

RLS response format compliance

Criteria
Without context
With context

Lead with SQL

0%

0%

Version-pinned URLs

100%

100%

Version admonition format

0%

100%

PG16 as SQL baseline

100%

100%

Provider-neutral managed limitations

0%

100%

BYPASSRLS superuser caveat

100%

100%

FORCE ROW LEVEL SECURITY

100%

100%

USING vs WITH CHECK

100%

100%

Section headers match references

50%

62%

Source links present

100%

100%

95%

39%

Diagnosing Slow Queries After Storage Upgrade

NVMe slow query investigation

Criteria
Without context
With context

NVMe random_page_cost

100%

100%

EXPLAIN ANALYZE BUFFERS

100%

100%

pg_stat_statements usage

100%

100%

CREATE STATISTICS recommendation

0%

100%

pg_stats not pg_statistic

100%

100%

pg_class filtered by relkind

62%

37%

Version-pinned URLs

0%

100%

PG16 baseline SQL

100%

100%

EXPLAIN bottom-up reading

0%

100%

Misestimate 10x threshold

0%

100%

100%

10%

AI-Powered Semantic Search for Product Catalog

pgvector semantic search setup

Criteria
Without context
With context

Extension named 'vector'

100%

100%

HNSW index chosen

100%

100%

Cosine opclass used

100%

100%

halfvec for memory savings

100%

100%

Iterative scan for filtered ANN

100%

100%

Provider-neutral managed phrasing

0%

100%

One opclass per index

100%

100%

ef_search / probes tuning

100%

100%

HNSW build memory

100%

100%

PG16 baseline SQL

100%

100%

Evaluated
Agent
Claude
Model
Claude Sonnet 4.6

Table of Contents