jbvc/postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
68
68%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (PostgreSQL/Supabase) and lists relevant capability areas, but remains at a category level rather than specifying concrete actions. The biggest weakness is the complete absence of a 'Use when...' clause, which is critical for Claude to know when to select this skill from a pool of many. The trigger terms are reasonable but could be expanded with common user phrasings.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about PostgreSQL queries, Supabase database setup, SQL performance issues, or database security policies.'
Include more natural trigger term variations such as 'postgres', 'SQL', 'slow queries', 'RLS', 'row level security', 'database performance', 'migrations'.
Make capabilities more concrete by listing specific actions, e.g., 'Writes optimized SQL queries, designs normalized schemas, creates indexes for performance, implements Row Level Security (RLS) policies.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PostgreSQL) and lists several action areas (query optimization, schema design, indexing, security), but these are categories rather than concrete specific actions like 'create indexes', 'write RLS policies', or 'optimize slow queries'. | 2 / 3 |
Completeness | Describes what the skill covers (PostgreSQL patterns for optimization, schema, indexing, security) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also only moderately detailed, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'PostgreSQL', 'query optimization', 'schema design', 'indexing', 'security', and 'Supabase', but misses common user variations like 'SQL', 'database performance', 'slow queries', 'RLS', 'row level security', 'migrations', or 'postgres'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of PostgreSQL and Supabase provides some distinctiveness, but 'database patterns', 'query optimization', and 'schema design' could overlap with general SQL skills or other database-related skills. The Supabase qualifier helps narrow it somewhat. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong reference-style skill that is highly concise and actionable, providing executable SQL patterns covering indexing, data types, common patterns, anti-pattern detection, and configuration. Its main weakness is the lack of workflow sequencing and validation checkpoints for multi-step or destructive operations (like system configuration changes), though it partially mitigates this by delegating complex workflows to the `database-reviewer` agent.
Suggestions
Add a brief validation/verification step after the Configuration Template section (e.g., 'Run SHOW work_mem; to confirm changes took effect') to address the missing feedback loop for system-altering commands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and practical. No explanations of what PostgreSQL is or how indexes work conceptually—just direct patterns, types, and executable SQL. The table format for index types and data types is extremely token-efficient. | 3 / 3 |
Actionability | All examples are fully executable SQL—composite indexes, covering indexes, partial indexes, RLS policies, upserts, cursor pagination, queue processing, and diagnostic queries are all copy-paste ready with clear comments explaining their purpose. | 3 / 3 |
Workflow Clarity | This is primarily a reference/cheat-sheet skill rather than a multi-step workflow skill. The 'When to Activate' section lists triggers but there's no sequenced workflow for tasks like migration creation or query optimization, and no validation checkpoints for potentially destructive operations like ALTER SYSTEM or REVOKE commands. | 2 / 3 |
Progressive Disclosure | The skill is well-structured as a quick reference overview with clear pointers to the `database-reviewer` agent for full workflows, and related skills for adjacent topics. Content is appropriately scoped—detailed enough to be useful but delegates deeper review to the agent. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents