Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is highly actionable with executable migration code across multiple ORMs, but it is padded with generic boilerplate, lacks explicit validation checkpoints in its destructive workflows, and promises reference files that do not exist in the bundle. Tightening the generic sections and adding real, well-split reference files would materially raise the score.
Suggestions
Remove or specialize the generic "Do not use this skill when" and "Instructions" sections, which read as boilerplate applicable to any skill and do not earn their tokens.
Add explicit validation/verification checkpoints (e.g. test on staging, verify row counts, confirm rollback succeeds) between the phases of the destructive zero-downtime and column-rename workflows, not just inside the single checkpoint-rollback example.
Create the referenced bundle files (references/orm-switching.md, references/schema-migration.md, references/data-transformation.md, references/rollback-strategies.md, assets/schema-migration-template.sql, assets/data-migration-script.py, scripts/test-migration.sh) or remove the dead links, and move the large inline code blocks into them so SKILL.md stays a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly concrete code without basic-concept padding, but the generic "Do not use this skill when" and "Instructions" sections plus repetitive queryInterface patterns across sections are boilerplate that could be tightened. | 2 / 3 |
Actionability | It provides fully executable, copy-paste-ready migration code with real commands (e.g. "npx sequelize-cli db:migrate", "npx prisma migrate dev --name create_users", "npm run typeorm migration:revert") across Sequelize, TypeORM, and Prisma. | 3 / 3 |
Workflow Clarity | Multi-step processes (zero-downtime phases, column-rename steps) are sequenced, but the destructive database workflows lack explicit validation checkpoints/feedback loops between steps, which the rubric caps at 2 for database operations despite one checkpoint-rollback example. | 2 / 3 |
Progressive Disclosure | Sections are well-labeled and a Resources section signals references with descriptions, but every referenced bundle file (references/*.md, assets/*, scripts/*) is absent and the heavy content that should be split remains inline in SKILL.md. | 2 / 3 |
Total | 9 / 12 Passed |