AC db-migrate
Database migration manager. Detects ORM/migration tool in use, generates migrations, handles rollbacks, creates seed scripts, diffs schemas between environments, backs up databases, and supports zero-downtime patterns. Use when the user says 'database migration', 'migrate', 'schema change', 'seed data', 'rollback', 'add a column', 'rename column', 'drop table', 'backfill', 'schema diff', or 'backup database'. Supports Prisma, Drizzle, Knex, TypeORM, Alembic, Django, raw SQL. Works with Postgres, MySQL, SQLite.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "required-tools" - note
frontmatter-keyunknown frontmatter key "security-notes"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (db-migrate) differs from the folder (database-migration-manager)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 43 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 3978 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 515: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (26 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.