Schema awareness - read before coding, type generation, prevent column errors
37
35%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/database-schema/SKILL.mdQuality
Discovery
14%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 reads as a loose collection of keywords rather than a coherent skill description. It fails to specify concrete actions, lacks a 'Use when...' clause, and is too vague to distinguish from other database or coding-related skills. The fragmented style makes it difficult for Claude to determine when this skill should be selected.
Suggestions
Rewrite as complete sentences specifying concrete actions, e.g., 'Reads database schema definitions before writing queries or application code. Generates TypeScript/language types from database schemas. Validates column names and types to prevent runtime errors.'
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks to write database queries, generate types from a schema, or when working with database tables and columns.'
Specify the technology domain (e.g., SQL databases, specific ORMs, specific languages for type generation) to reduce conflict risk with other coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, fragmented phrases like 'schema awareness', 'read before coding', and 'prevent column errors' without listing concrete actions. It's unclear what specific operations this skill performs. | 1 / 3 |
Completeness | The description weakly addresses 'what' through fragmented phrases and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Terms like 'schema', 'type generation', and 'column errors' are somewhat relevant keywords a developer might use, but they lack common variations and natural phrasing (e.g., 'database schema', 'SQL', 'ORM', 'migrations', 'table structure'). | 2 / 3 |
Distinctiveness Conflict Risk | 'Schema awareness' and 'type generation' are broad concepts that could overlap with database skills, ORM skills, TypeScript type generation, API schema skills, and many other coding-related skills. | 1 / 3 |
Total | 5 / 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 is highly actionable with excellent workflow clarity, providing concrete executable examples and clear validation checkpoints for database schema awareness. However, it is severely bloated—full ORM examples for 4+ frameworks, repetitive checklists, and template content that Claude already knows how to produce are all inlined, consuming excessive tokens. The content desperately needs progressive disclosure: framework-specific examples should be split into referenced files, leaving the main skill lean.
Suggestions
Reduce the main SKILL.md to ~80 lines: keep the core rule, schema file locations table, pre-code checklist, and anti-patterns. Move all framework-specific code examples (Drizzle, Prisma, Supabase, SQLAlchemy) into separate referenced files like `examples/drizzle.md`.
Remove the full schema reference template example—Claude knows how to create markdown tables. Replace with a one-line instruction: 'Create _project_specs/schema-reference.md listing all tables with columns, types, nullable, defaults, and relationships.'
Consolidate the three separate checklists (Pre-Code, Setup, Per-Task) into a single concise checklist to reduce redundancy.
Remove explanations Claude already knows (e.g., what type generation does, why raw SQL is dangerous) and keep only the actionable commands and constraints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ 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 ASCII box diagrams, and repetitive checklists significantly bloat the content. Much of this could be condensed to a table of commands and a single example. | 1 / 3 |
Actionability | Provides fully executable code examples across multiple ORMs, specific CLI commands for type generation and migrations, concrete type-safe query examples showing correct vs incorrect usage, and a detailed schema reference template. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints: the pre-code checklist, schema-aware TDD workflow, and migration workflow all include verification steps and feedback loops (type check → fix → re-validate). The session start protocol provides clear sequencing. | 3 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files despite being a perfect candidate for splitting (e.g., per-ORM examples into separate files, schema reference template into its own file). All content is inline, making the skill overwhelming to consume in context. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 | |
7e5f7a2
Table of Contents
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.