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' clause and identifies the domain well (PostgreSQL schema design/review), which is its main strength. However, it lists topic categories rather than concrete actions, and misses common trigger term variations like 'Postgres', 'database design', or 'table structure'. Adding specific actions and broader keyword coverage would significantly improve skill selection accuracy.
Suggestions
Replace category listings with concrete actions, e.g., 'Designs tables, selects appropriate data types, creates indexes, defines constraints and foreign keys, applies normalization and partitioning strategies'.
Add common trigger term variations: 'Postgres', 'database design', 'table structure', 'DDL', 'CREATE TABLE', 'migrations', '.sql files'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (PostgreSQL schema) and lists several areas it covers (data types, indexing, constraints, performance patterns, advanced features), but these are categories rather than concrete actions. It doesn't list specific actions like 'create indexes', 'define foreign keys', or 'normalize tables'. | 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, but misses common user variations like 'Postgres', 'database design', 'table structure', 'DDL', 'migrations', '.sql', or 'CREATE TABLE'. | 2 / 3 |
Distinctiveness Conflict Risk | The PostgreSQL-specific qualifier helps distinguish it from general database skills, but 'performance patterns' and 'advanced features' are vague enough to potentially overlap with PostgreSQL query optimization or general database performance 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 strong concrete examples and clear 'do/don't' guidance. Its main weaknesses are length—it tries to cover everything in one file rather than using progressive disclosure—and the lack of explicit validation workflows for risky operations like schema migrations and bulk data loads. The content quality is high but would benefit from splitting into a concise overview with linked reference files.
Suggestions
Split detailed sections (JSONB Guidance, Partitioning, Extensions, Data Types) into separate reference files and link from the main SKILL.md with brief summaries to improve progressive disclosure and reduce token cost.
Add an explicit step-by-step workflow with validation checkpoints for schema evolution/migration, e.g., 'BEGIN → ALTER → validate → COMMIT/ROLLBACK' with concrete commands.
Trim explanatory asides that Claude already knows (e.g., what sequence gaps are, what MVCC dead tuples are, what TOAST is) to just the actionable implication.
| 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 exhaustive TOAST storage explanation, the full enumeration of geometric types). Some items like explaining what MVCC dead tuples are or what gaps in sequences mean border on unnecessary for Claude. | 2 / 3 |
Actionability | The skill provides concrete, executable SQL examples throughout—CREATE TABLE statements, CREATE INDEX commands, specific syntax for constraints, partitioning, JSONB indexing, and generated columns. The examples section at the end is copy-paste ready, and guidance like 'DO NOT use X; DO use Y' is immediately actionable. | 3 / 3 |
Workflow Clarity | The skill covers many topics clearly but lacks explicit multi-step workflows with validation checkpoints. The 'Safe Schema Evolution' section hints at workflows (transactional DDL, testing with ROLLBACK) but doesn't provide a clear step-by-step process with validation gates. For destructive operations like schema changes or bulk loads, explicit feedback loops are missing. | 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 Extensions could be split into separate reference files with brief summaries in the main skill, reducing the overall length significantly. | 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
70444e5
- 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.