axiom-audit-database-schema

Use when the user mentions database schema review, migration safety, GRDB migration audit, or SQLite schema checking.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-audit-database-schema/SKILL.md

Quality

Content

85%Weight 40%Scale 1-5

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

A highly actionable, well-sequenced auditor workflow with concrete grep patterns, fix code, and explicit verification checkpoints. Its main weakness is progressive disclosure: all content lives in one inline file with no reference bundles to defer detail to.

Suggestions

Move the 10 detection-pattern details (search/verify/fix per pattern) into a references/ file (e.g. PATTERNS.md), keeping SKILL.md as an overview that signals the deeper file.

Extract the Phase 4 cross-reference and Phase 5 scoring tables into a separate reference doc to reduce inline weight.

Add clearly signaled one-level-deep references (e.g. 'See references/PATTERNS.md for full detection details') so navigation is explicit rather than monolithic.

Dimension	Reasoning	Score
Conciseness	The body is dense and action-oriented with no padding about what SQLite/GRDB are; each 'Issue' line states a domain-specific migration gotcha concisely. A few explanatory lines could be trimmed, so it stops just short of fully lean.	4 / 5
Actionability	Runnable Grep/Glob patterns, copy-paste-ready fix snippets ('ADD COLUMN name TEXT NOT NULL DEFAULT ''', 'INSERT ... ON CONFLICT(id) DO UPDATE SET ...') and concrete PRAGMA commands cover the common cases throughout all 10 patterns.	5 / 5
Workflow Clarity	Phases 1-5 are explicitly sequenced with validation checkpoints ('use Read to verify the surrounding context before reporting', 'Present this map in the output before proceeding'), a false-positives checklist, and compound-finding cross-references — satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	The ~260-line body is well-sectioned by phases and patterns, but no bundle files exist and everything (the 10 detection patterns, cross-reference and scoring tables) is inlined rather than split into one-level-deep reference files, fitting 'Some structure but content that should be separate is inline'.	3 / 5
	Total	17 / 20 Passed

Description

60%Weight 40%Scale 1-5

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 has strong trigger-term coverage and a distinct niche, but it leads with the 'when' and leaves the 'what' only implied, with no concrete capability verbs. Rewording to state the action first would raise specificity and completeness.

Suggestions

Lead with a concrete capability verb, e.g. 'Audits database schemas and migrations for anti-patterns and data-loss risks', then keep the 'Use when...' clause.

Name 1-2 concrete actions the skill performs (e.g. 'detects NOT NULL-without-DEFAULT crashes, flags unenforced foreign keys') to lift specificity above 2.

Ensure the 'what' is explicitly stated rather than inferred from the trigger nouns, so both what and when are answered concretely.

Dimension	Reasoning	Score
Specificity	The description names the domain ('database schema review, migration safety, GRDB migration audit, SQLite schema checking') but states no concrete action verbs — the capability is only implied through trigger nouns, matching 'Names the domain but actions are minimal or generic'.	2 / 5
Completeness	It has an explicit 'when' ('Use when the user mentions...') but the 'what' is only weakly implied through the trigger nouns with no stated capability verb, fitting 'Has a clear what but when is missing or only weakly implied' inverted — explicit when, implied what.	3 / 5
Trigger Term Quality	Good keyword coverage across natural phrases a user would say ('database schema review', 'migration safety', 'GRDB migration audit', 'SQLite schema checking') with framework-specific synonyms; a few common variations like 'check my migrations' are absent, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche (GRDB/SQLite schema and migration auditing) with distinct, framework-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	14 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-audit-database-schema/SKILL.md
Commit: 4ae86a3

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.