Content
65%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A dense, largely executable reference whose code quality and conciseness are strong. The main deficits are a never-defined Profile entity that breaks self-contained executability, missing validation checkpoints around destructive migration operations, and a monolithic single-file layout that inlines full entity source that would sit better in reference files.
Suggestions
Add validation checkpoints to the migration workflow (e.g., 'Run npx typeorm migration:show -d src/data-source.ts before and after migration:run to verify state; never run schema:drop without confirming the target database').
Define the missing Profile entity (or remove the OneToOne relation and transaction example that references it) and make the schema:sync command consistent by always including the -d flag.
Move the full entity, subscriber, and transaction source listings into a references/ file (e.g., references/entities.md), keeping SKILL.md to the structure map, key conventions, and one compact example per pattern.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dominated by lean, executable code with almost no explanation of concepts Claude already knows; the only fat is minor duplication — the opening blockquote restates the frontmatter description, and the migration generate/run/schema:sync commands appear in both 'Database Initialization' and 'Common Commands'. | 4 / 5 |
Actionability | Nearly everything is copy-paste ready (install commands, tsconfig flags, DataSource config, entities, repository functions, subscriber, transaction), but there are concrete gaps: the User entity and transaction example import a 'Profile' entity that is never defined or listed in the project structure, 'npx typeorm schema:sync' appears once without the required '-d' flag, and the install line hardcodes the 'pg' driver despite advertising MySQL/SQLite support. | 4 / 5 |
Workflow Clarity | The scaffold-to-migration sequence is implicit in the section ordering and commands exist, but workflows involving destructive/batch database operations (schema:sync, schema:drop, migration:run) lack explicit validation checkpoints such as 'run migration:show to verify state before/after' — the missing-feedback-loop guideline caps this at 3. It is not a 2 because the commands themselves are correct and well-ordered. | 3 / 5 |
Progressive Disclosure | Sections are clearly organized with headers and a project-structure map, but the ~250 lines of complete entity/repository/subscriber source code are inline reference material in a single SKILL.md with no bundle files, fitting the 'content that should be separate is inline' anchor rather than the well-split 4. | 3 / 5 |
Total | 14 / 20 Passed |