postgres-pro
Use when optimizing PostgreSQL queries, configuring replication, or implementing advanced database features. Invoke for EXPLAIN analysis, JSONB operations, extension usage, VACUUM tuning, performance monitoring.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly identifies PostgreSQL-specific capabilities with concrete actions and explicit trigger conditions. It uses natural keywords that users would employ when seeking PostgreSQL help, and its focus on PostgreSQL-specific features (JSONB, VACUUM, EXPLAIN) makes it highly distinctive. The only minor note is that it lacks a 'what it does' preamble—it jumps straight into 'Use when' without a brief capability summary sentence—but the trigger clauses themselves effectively communicate the capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: optimizing PostgreSQL queries, configuring replication, EXPLAIN analysis, JSONB operations, extension usage, VACUUM tuning, and performance monitoring. | 3 / 3 |
Completeness | Explicitly answers both 'what' (optimizing queries, configuring replication, EXPLAIN analysis, JSONB operations, VACUUM tuning, etc.) and 'when' with clear trigger guidance ('Use when optimizing PostgreSQL queries...', 'Invoke for EXPLAIN analysis...'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'PostgreSQL', 'queries', 'replication', 'EXPLAIN', 'JSONB', 'VACUUM', 'performance monitoring', 'extension'. These cover common terms a user working with PostgreSQL would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to PostgreSQL-specific features (EXPLAIN, JSONB, VACUUM, extensions, replication), making it highly distinct from generic database or SQL skills. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable PostgreSQL skill with excellent executable examples and a well-structured workflow that includes proper validation checkpoints. Its main weaknesses are minor verbosity (persona description, redundant knowledge listing, some obvious constraints) and uncertainty around the referenced files which aren't provided in the bundle. The content strikes a good balance between being a quick reference and providing enough depth for common tasks.
Suggestions
Remove the opening persona sentence and the 'Knowledge Reference' line — these add no actionable value and waste tokens.
Trim constraints that Claude already knows (e.g., 'Use prepared statements to prevent SQL injection', 'Use uuid type for UUIDs') to focus on PostgreSQL-specific non-obvious guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good code examples, but includes some unnecessary content like the 'Knowledge Reference' line which just lists technologies Claude already knows, the 'When to Use This Skill' section largely duplicates the description, and some constraints are common knowledge for Claude (e.g., 'Use prepared statements to prevent SQL injection'). The opening sentence describing the skill's persona is also unnecessary. | 2 / 3 |
Actionability | The skill provides fully executable SQL examples throughout — from identifying slow queries via pg_stat_statements, to creating partial indexes with CONCURRENTLY, to JSONB GIN indexing, VACUUM monitoring, and replication lag checks. All code is copy-paste ready with inline comments explaining what to look for. | 3 / 3 |
Workflow Clarity | The end-to-end example provides a clear 5-step sequence (identify → analyze → fix → verify → update stats) with explicit validation checkpoints (verify index is used with EXPLAIN, confirm lower actual time). The core workflow also includes verification steps ('verify with EXPLAIN before deploying', 'verify improvements after each change'). The constraints section reinforces validation requirements. | 3 / 3 |
Progressive Disclosure | The reference table pointing to 5 topic-specific files (references/performance.md, references/jsonb.md, etc.) is well-structured with clear 'Load When' guidance. However, no bundle files are provided, so these references are unverifiable. Additionally, some inline content (Common Patterns section) overlaps with what the referenced files likely cover, suggesting the split between overview and detail could be cleaner. | 2 / 3 |
Total | 10 / 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
- jeffallan/claude-skills
- Commit
e8be415
- 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.