AB sql-db-toolkit
Comprehensive SQL database toolkit for querying, schema inspection, data export, and migration management. Use when the user wants to: (1) Query a database with SELECT/INSERT/UPDATE/DELETE, (2) Inspect table schemas, indexes, and foreign keys, (3) Export data to CSV/JSON, (4) Generate SQL migrations or schema diffs, (5) Run database backups and restore, (6) Analyze query performance with EXPLAIN, (7) Work with SQLite, PostgreSQL, MySQL, or any sqlalchemy-compatible database.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, progress reporting
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Comprehensive SQL database toolkit for querying, schema inspection… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 482 tokens
- 100Running it twice. No mutating operations
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)
- +1No license
- +2Single-language instructions
- +3Description length 479: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 5 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.