CtrlK
BlogDocsLog inGet started
Tessl Logo

postgresql-table-design

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

81

1.27x
Quality

Does it follow best practices?

Impact

92%

1.27x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is exceptionally lean and actionable with executable SQL throughout, but it is a monolithic single-file reference lacking progressive disclosure into bundle files and explicit validation feedback loops for destructive DDL operations.

Suggestions

Split the large reference sections (Data Types, Extensions, JSONB Guidance) into separate reference files and link to them one level deep from SKILL.md to improve progressive disclosure.

Add explicit validation checkpoints for destructive/batch DDL — e.g. wrap migrations in transactions and verify with a query before committing, or run a dry-run check after schema changes.

Add a brief 'safe migration workflow' (test in transaction -> validate -> commit) to convert the scattered evolution notes into a sequenced, checkpointed process.

DimensionReasoningScore

Conciseness

Dense, declarative bullet lists with zero introductory padding — e.g. 'Prefer TIMESTAMPTZ for event time; NUMERIC for money' — assume Claude's competence and earn every token, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Provides executable SQL throughout — copy-paste-ready examples (Users/Orders/JSONB tables), concrete commands ('CREATE INDEX CONCURRENTLY', 'ALTER TABLE ... SET STORAGE'), and exact syntax, matching the 'fully executable' anchor.

3 / 3

Workflow Clarity

Sequenced guidance exists in places (e.g. 'BEGIN; ALTER TABLE...; ROLLBACK', 'drop index, load data, recreate indexes') but there are no explicit validation checkpoints or validate-fix-retry feedback loops for destructive/batch DDL, which the scoring notes say should cap workflow_clarity at 2.

2 / 3

Progressive Disclosure

Content is well-organized into clear sections, but the SKILL.md is a ~200-line monolithic body with no bundle files or one-level-deep references to split out the large reference material (data types, extensions, JSONB guidance), matching the 'some structure but content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

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 is specific and clearly niche-scoped to PostgreSQL schema design, but it omits any 'Use when...' trigger guidance, which caps completeness and weakens trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when designing tables, choosing data types, or setting up indexes/constraints in PostgreSQL.'

Include more natural user-facing terms like 'tables', 'database design', and 'DDL' alongside the technical vocabulary.

Reframe as concrete actions ('Designs tables, selects data types, defines indexes and constraints') rather than the passive 'Covers best-practices, ...'.

DimensionReasoningScore

Specificity

Names multiple concrete capability areas — 'data types, indexing, constraints, performance patterns, and advanced features' — matching the rubric's 'Lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers 'what' (design a PostgreSQL schema covering listed areas) but has no 'Use when...' clause or equivalent trigger guidance, capping completeness at 2 per the judging guidelines.

2 / 3

Trigger Term Quality

Contains domain keywords ('PostgreSQL', 'schema', 'indexing', 'constraints') but lacks the common natural variations a user would say ('tables', 'database design', 'DDL'); partial coverage per the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The PostgreSQL-specific framing carves a clear niche distinct from generic database skills, making false-triggers unlikely; matches the 'clear niche with distinct triggers' anchor.

3 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Dicklesworthstone/pi_agent_rust
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.