database-schema

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

Quality

38%

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 or provide any trigger guidance. The dash-separated phrase style reads like shorthand notes rather than a proper skill description.

Suggestions

Rewrite as complete sentences describing concrete actions, e.g., 'Reads database schema definitions before writing queries or application code. Generates TypeScript/language types from database table structures. Validates column names and types to prevent runtime errors.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about database schemas, table structures, column types, generating types from a database, or needs to verify column names before writing queries.'

Include specific file types, technologies, or formats (e.g., SQL, PostgreSQL, Prisma, ORM, .sql files) to improve trigger term coverage and distinctiveness.

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 at all. The description fails to clearly answer either question.	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 term 'schema awareness' provides some niche specificity, but the vague phrasing like 'read before coding' and 'prevent column errors' could overlap with general database skills, code review skills, or data validation skills.	2 / 3
	Total	6 / 12 Passed

Implementation

55%

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 idea (read schema before writing database code) and provides excellent actionable guidance with executable examples and clear workflows. However, it is severely bloated — full ORM model definitions for 4+ frameworks, complete Pydantic schemas, and template schema reference files consume enormous token budget for information Claude already knows. The content desperately needs to be split into a concise overview with references to per-stack detail files.

Suggestions

Reduce the main file to ~50-60 lines covering the core rule, checklist, and session start protocol, moving per-stack ORM examples into separate reference files (e.g., `schema-drizzle.md`, `schema-prisma.md`)

Remove the full schema reference template example — a 2-line description of what it should contain is sufficient since Claude can generate markdown tables

Remove the SQLAlchemy Pydantic model example and full ORM class definitions — Claude knows how to write these; just reference the file paths and type generation commands

Add a 'Quick start' section at the top with just the 4-step core rule and the stack-specific schema location table, deferring everything else to linked files

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~250+ lines. Includes extensive ORM examples for 4+ frameworks (Drizzle, Prisma, Supabase, SQLAlchemy) that Claude already knows how to write. The schema reference template, full model definitions, and Pydantic examples are boilerplate 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 stacks, concrete commands for type generation and migrations, specific file paths, and copy-paste ready schema definitions. The checklist format and type-safe query examples with correct/incorrect comparisons are highly actionable.	3 / 3
Workflow Clarity	Clear multi-step workflows with explicit validation checkpoints: the Schema-Aware TDD workflow, Migration Workflow, and Session Start Protocol all have numbered sequences with validation steps (type check, re-validate, fix and retry). The pre-code checklist serves as an explicit verification gate before proceeding.	3 / 3
Progressive Disclosure	Monolithic wall of text with everything inline. The per-stack ORM examples (Drizzle, Prisma, Supabase, SQLAlchemy) should be in separate reference files. No external file references for detailed content — everything is dumped into a single document making it hard to navigate and consuming excessive context window.	1 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: d4ddb03

Reviewed: 3 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.