comparing-database-schemas

Process use when you need to work with schema comparison. This skill provides database schema diff and sync with comprehensive guidance and automation. Trigger with phrases like "compare schemas", "diff databases", or "sync database schemas".

Quality

70%

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 ./plugins/database/database-diff-tool/skills/comparing-database-schemas/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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

The skill provides a well-sequenced, concrete comparison workflow with a validation step and a useful error-handling table, but it stops short on the generation deliverables, lacks a failure-recovery feedback loop for destructive database ops, and fails to integrate its own bundled script while listing phantom bundle files. The truncated Overview is an additional content defect.

Suggestions

Add the missing failure-recovery branch to step 10: "If the second diff is non-empty, revise the migration SQL and re-run against the copy until it reports zero differences; only then apply to the target."

Reference and actually use the bundled script (or replace it): either point step 8–9 to scripts/generate_migration_script.py with invocation examples, or remove it; and delete the phantom entries from scripts/README.md and assets/README.md that have no corresponding files.

Provide concrete, copy-paste-ready SQL scaffolding for the migration-generation step (CREATE/ALTER/DROP templates with transaction wrapping) instead of only describing the statements to generate, and complete the truncated Overview sentence.

Dimension	Reasoning	Score
Conciseness	The instructions are mostly lean and assume Claude's competence (concrete SQL and CLI commands, no basic-concept explanations), but the narrative Examples section and the truncated Overview ("staging vs.") add padding and a defect, so it does not reach the every-token-earns-its-place bar of level 3.	2 / 3
Actionability	Steps 1–7 give concrete, executable SQL and pg_dump/mysqldump commands, but the core deliverable steps (8–9: generating the diff report and migration SQL) only describe output rather than providing complete executable code, and the bundled generate_migration_script.py — a generic placeholder — is never referenced, leaving key details missing per the level-2 anchor.	2 / 3
Workflow Clarity	The 10-step sequence is clearly ordered with an explicit validation step (step 10: apply to a copy and re-run the diff expecting zero differences), but for destructive database operations the rubric requires a full validate->fix->retry loop; only the validate half is present with no failure-recovery branch or "only proceed when valid" gate, capping it at 2.	2 / 3
Progressive Disclosure	The body is organized into clear sections rather than a wall of text, but the existing bundle file generate_migration_script.py is never referenced from the body, and the scripts/assets READMEs list files (rollback_migration.py, validate_schema_changes.py, migration_template.sql) that do not exist, so references are poorly signaled and partially broken per the level-2 anchor.	2 / 3
	Total	8 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 clearly communicates a well-scoped niche with explicit, natural trigger phrases and answers both what and when. Its main weakness is specificity: the capability statement leans on marketing filler ("comprehensive guidance and automation") and the opening "Process use when" fragment is garbled.

Suggestions

Replace "with comprehensive guidance and automation" with concrete deliverables, e.g. "Generates a categorized diff report and a transactional migration SQL script to sync the target database to the source."

Fix the garbled opening "Process use when you need to work with schema comparison." to a clean third-person clause such as "Use when you need to compare or synchronize database schemas."

Dimension	Reasoning	Score
Specificity	It names the domain and two actions ("database schema diff and sync") but pads them with vague fluff ("comprehensive guidance and automation") and does not list multiple distinct concrete actions, matching the level-2 anchor rather than level 3.	2 / 3
Completeness	It answers both what ("database schema diff and sync") and when with an explicit trigger clause ("use when you need to work with schema comparison" plus enumerated trigger phrases), satisfying the level-3 anchor; the 'Use when' guidance is present so it is not capped at 2.	3 / 3
Trigger Term Quality	It supplies natural phrases a user would actually say — "compare schemas", "diff databases", "sync database schemas" — giving good coverage of common variations, matching the level-3 anchor.	3 / 3
Distinctiveness Conflict Risk	It targets a clear niche (database schema comparison) with distinct, domain-specific triggers unlikely to fire for unrelated skills, matching the level-3 anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/database/database-diff-tool/skills/comparing-database-schemas/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.