database-schema

Schema awareness - read before coding, type generation, prevent column errors

Quality

42%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/database-schema/SKILL.md

Quality

Discovery

22%

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 description is too terse and fragmented to effectively guide skill selection. It hints at a database schema inspection workflow but fails to articulate concrete actions, specify the domain clearly, or provide any trigger conditions. The comma-separated fragments read like internal notes rather than a functional description.

Suggestions

Rewrite as complete sentences describing concrete actions, e.g., 'Reads database schema definitions to generate TypeScript types and prevent column name mismatches in queries.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user is writing database queries, generating types from a schema, or encountering column-related errors.'

Include specific technology keywords users might mention, such as 'database', 'SQL', 'table schema', 'ORM', 'TypeScript types', or 'migrations'.

Dimension	Reasoning	Score
Specificity	The description uses vague, fragmented phrases like 'read before coding', 'type generation', and 'prevent column errors' without clearly describing concrete actions. It reads more like a list of abstract goals than specific capabilities.	1 / 3
Completeness	The 'what' is only vaguely implied through fragments, and there is no 'when' clause or explicit trigger guidance. The description lacks a 'Use when...' clause, which per the rubric should cap completeness at 2, but the 'what' is also very weak, warranting a 1.	1 / 3
Trigger Term Quality	Contains some relevant keywords like 'schema', 'type generation', and 'column errors' that could match user queries about database schemas, but misses common variations like 'database', 'SQL', 'table structure', 'ORM', or specific technologies.	2 / 3
Distinctiveness Conflict Risk	The mention of 'schema awareness' and 'column errors' provides some specificity toward database-related work, but the vague phrasing could overlap with general database skills, code generation skills, or type-safety skills.	2 / 3
	Total	6 / 12 Passed

Implementation

62%

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

The skill has a strong core concept (read schema before coding) with excellent actionability and workflow clarity, but is severely undermined by verbosity. Full ORM schema definitions for four frameworks, complete Pydantic models, and detailed migration commands bloat the file far beyond what's needed — Claude already knows how to write Drizzle schemas and Prisma models. The content would be dramatically more effective at 1/4 its current length with framework-specific details in separate referenced files.

Suggestions

Cut the full ORM schema examples (Drizzle, Prisma, Supabase, SQLAlchemy) to a single representative example inline, and move framework-specific details to separate referenced files like `drizzle-schema.md`, `prisma-schema.md`, etc.

Remove the schema-reference.md template example — Claude can generate table documentation formats on demand. Replace with a one-line instruction: 'Create a schema-reference.md with table/column/type/nullable/default info.'

Consolidate the anti-patterns list and common mistakes table — they largely repeat the same points (read schema, use types, don't guess columns).

Remove the SQLAlchemy Pydantic schema example entirely — it's teaching Claude basic Pydantic usage which it already knows.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Includes full ORM schema examples for 4+ frameworks (Drizzle, Prisma, Supabase, SQLAlchemy) that Claude already knows how to write. The schema reference template, multiple complete model definitions, and Pydantic examples are all things Claude can generate on demand. The core insight ('read schema before coding') could be conveyed in ~30 lines.	1 / 3
Actionability	Provides fully executable code examples across multiple frameworks, specific commands for type generation and migrations, concrete checklists, and copy-paste ready query examples with correct/incorrect comparisons. Every recommendation is backed by specific, runnable code.	3 / 3
Workflow Clarity	Clear sequential workflows with explicit validation checkpoints for both the TDD workflow and migration workflow. The pre-code checklist serves as a validation gate, the migration workflow includes type-checking as a verification step, and there are feedback loops (fix type errors → re-validate).	3 / 3
Progressive Disclosure	Content is structured with clear headers and sections, but it's monolithic — all framework-specific examples are inline rather than split into separate files. The per-framework type generation examples (Drizzle, Prisma, Supabase, SQLAlchemy) would be better as referenced files, keeping the main skill focused on the core workflow.	2 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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: alinaqi/claude-bootstrap
Commit: 24cfe58

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.