postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features
73
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/database-design/skills/postgresql/SKILL.mdQuality
Discovery
67%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 has a clear 'Use when' trigger clause and identifies the domain well (PostgreSQL schema design/review). However, it lists topic categories rather than concrete actions, and could benefit from more natural trigger terms and specific capability descriptions. The use of second person ('Use this skill') is noted but the rubric specifically penalizes first/second person voice for specificity.
Suggestions
Replace category listings with concrete actions, e.g., 'Designs table structures, selects appropriate data types, creates indexes, defines constraints, and optimizes query performance for PostgreSQL schemas'.
Add more natural trigger term variations such as 'Postgres', 'database design', 'table design', 'DDL', 'CREATE TABLE', 'migrations', or '.sql files'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PostgreSQL schema) and lists several topic areas (data types, indexing, constraints, performance patterns, advanced features), but these are categories rather than concrete actions. It doesn't specify actions like 'create indexes', 'normalize tables', or 'write migration scripts'. | 2 / 3 |
Completeness | Explicitly answers both 'what' (covers best-practices, data types, indexing, constraints, performance patterns, advanced features) and 'when' ('Use this skill when designing or reviewing a PostgreSQL-specific schema'). The 'Use when' clause is present and clear. | 3 / 3 |
Trigger Term Quality | Includes 'PostgreSQL', 'schema', 'indexing', 'constraints', 'data types' which are relevant keywords. However, it misses common user variations like 'Postgres', 'database design', 'table structure', 'DDL', 'migrations', '.sql', or 'CREATE TABLE'. | 2 / 3 |
Distinctiveness Conflict Risk | The PostgreSQL-specific focus helps distinguish it from general database skills, but 'performance patterns' and 'advanced features' are vague enough to potentially overlap with general SQL optimization or database administration skills. The 'schema' focus narrows it somewhat but could still conflict with broader database design skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable PostgreSQL schema design reference with excellent concrete examples and specific guidance. Its main weaknesses are its length (could benefit from splitting detailed subsections into referenced files) and the lack of explicit multi-step workflows with validation checkpoints for operations like schema migrations or bulk data loading. The content is well-structured but would benefit from progressive disclosure to reduce the token footprint of the main skill file.
Suggestions
Extract detailed subsections (Data Types catalog, JSONB Guidance, Partitioning, Extensions) into separate referenced files to reduce the main skill's token footprint and improve progressive disclosure.
Add explicit step-by-step workflows with validation checkpoints for schema evolution and bulk load operations (e.g., 1. Test in transaction → 2. Validate → 3. Apply → 4. Verify).
Trim explanatory asides that Claude already knows (e.g., what MVCC dead tuples are, what COPY does, that rollbacks create gaps) to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts Claude already knows, but it's quite long with some sections that could be tightened (e.g., the TOAST storage details, extensive data type catalog). Some items like explaining what MVCC dead tuples are or what COPY does border on unnecessary for Claude. | 2 / 3 |
Actionability | Provides concrete, executable SQL examples throughout (CREATE TABLE, CREATE INDEX, specific syntax), specific operator references, exact function names, and copy-paste ready code blocks. The examples section at the end demonstrates complete, runnable table definitions with indexes and constraints. | 3 / 3 |
Workflow Clarity | The skill covers many topics but lacks explicit multi-step workflows with validation checkpoints. The 'Safe Schema Evolution' section lists tips but doesn't provide a sequenced workflow. For destructive operations like schema changes or bulk loads, there are no validate-then-proceed feedback loops—just individual tips. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and logical sections, but it's a monolithic document with no references to external files for deep-dive topics. Sections like JSONB Guidance, Partitioning, and the extensive Data Types catalog could be split into separate reference files with links from the main skill. | 2 / 3 |
Total | 9 / 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.
- Repository
- wshobson/agents
- Commit
91fe43e
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.