database-migration
Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.
79
67%
Does it follow best practices?
Impact
99%
1.08xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/framework-migration/skills/database-migration/SKILL.mdQuality
Discovery
92%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 is a strong description that clearly articulates specific capabilities and includes an explicit 'Use when' clause with relevant trigger terms. The main weakness is that its broad scope ('across ORMs and platforms') and some general terms like 'data transformations' could create overlap with other database or ETL-related skills. Overall, it follows the pattern of the good examples closely.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Execute database migrations', 'zero-downtime strategies', 'data transformation', and 'rollback procedures'. Also mentions 'across ORMs and platforms' which adds specificity about scope. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute database migrations with zero-downtime strategies, data transformation, rollback procedures across ORMs) and 'when' (explicit 'Use when' clause covering migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'database migrations', 'schemas', 'data transformations', 'zero-downtime', 'rollback', 'ORMs', 'deployment strategies'. These cover common variations of how users would describe migration-related tasks. | 3 / 3 |
Distinctiveness Conflict Risk | While 'database migrations' and 'zero-downtime' are fairly distinct, terms like 'data transformations' and 'changing schemas' could overlap with general database management or ETL-focused skills. The scope is broad ('across ORMs and platforms') which increases potential conflict with ORM-specific or platform-specific skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code examples across multiple ORMs and migration scenarios, which is its primary strength. However, it is excessively verbose—much of the content covers basic patterns Claude already knows (creating tables, adding columns), and the monolithic structure with no progressive disclosure wastes significant context window space. Validation checkpoints are present in some examples but inconsistently applied across the workflows.
Suggestions
Reduce content by 60%+: Remove basic table creation examples (Claude knows these), keep only the non-obvious patterns like zero-downtime column renames, checkpoint-based rollback, and cross-database handling.
Split into separate files: Create ORM-specific reference files (SEQUELIZE.md, TYPEORM.md, PRISMA.md) and keep SKILL.md as a concise overview with links.
Add explicit validation steps to data transformation workflows—e.g., verify row counts before/after, check for NULL values in transformed columns, and include a 'validate before proceeding' checkpoint.
Remove the 'When to Use This Skill' section entirely—it's pure padding that tells Claude nothing actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. The 'When to Use This Skill' bullet list is unnecessary padding. Showing nearly identical create-users migrations across three ORMs (Sequelize, TypeORM, Prisma) is redundant—Claude knows how to write basic table creation migrations. Many examples are trivially simple (adding a column with a default) and don't earn their token cost. | 1 / 3 |
Actionability | All code examples are fully executable with real syntax, specific CLI commands for running/rolling back migrations, and concrete patterns for each ORM. The examples are copy-paste ready with proper imports, file naming conventions, and complete up/down methods. | 3 / 3 |
Workflow Clarity | The zero-downtime section outlines a clear multi-phase sequence (Phases 1-5), and the checkpoint-based rollback includes verification. However, most migration workflows lack explicit validation checkpoints—the renaming columns example says 'Step 2: Update application to use new column' without any verification that data was copied correctly. The data transformation section processes records one-by-one with no batch validation or progress checking. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code examples with no references to external files. At this length, the ORM-specific examples, cross-database migration details, and data transformation patterns should be split into separate reference files. Everything is inline with no navigation aids or links to deeper content. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%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
- wshobson/agents
- Commit
91fe43e
- Reviewed
Table of Contents
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.