Content
92%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 and concise with a well-sequenced workflow that includes an explicit validation loop. Its main weakness is progressive disclosure: a usable bundled generator script exists but is never surfaced from SKILL.md.
Suggestions
Reference the bundled generator from the relevant step, e.g. "Run `python scripts/generate_migration_script.py` to emit the migration SQL from the diff report".
Consider moving the Error Handling table and/or Examples into references/ files linked from the body to keep SKILL.md a true overview.
Fix the truncated Overview sentence ("staging vs.") so the section reads as a complete thought.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence, leading with concrete SQL queries and CLI commands rather than explaining what databases or schemas are; nearly every line is actionable rather than padded. | 3 / 3 |
Actionability | It provides copy-paste-ready executable commands (pg_dump, mysqldump) and specific information_schema / pg_catalog queries for each comparison category, leaving little abstract about how to perform the work. | 3 / 3 |
Workflow Clarity | A clear 10-step numbered sequence culminates in an explicit validation feedback loop (step 10: apply the migration to a copy and re-run the diff expecting zero differences), satisfying the validation checkpoint requirement for destructive database operations. | 3 / 3 |
Progressive Disclosure | Sections are well-organized, but the body is essentially monolithic: the bundled scripts/generate_migration_script.py and the references/assets directories are never referenced or linked from the body, and inline content (error handling, examples) that could live in separate files is not split out. | 2 / 3 |
Total | 11 / 12 Passed |