AF sql-review
Pre-commit SQL code review for uncommitted database changes. Detects antipatterns that cause real production incidents — broken TRY/CATCH error handling, swallowed errors, retry patterns without loops, tables missing PK/indexes, type-mismatch truncation, dynamic-SQL injection, NOLOCK in write paths, UPDATE/DELETE without WHERE, hardcoded env values, cross-DB refs, and more (full catalog in the skill body). Reports BLOCKER/WARN/INFO findings with file:line citations and fixes. Never edits SQL. Use this skill whenever the user says "/sql-review", "review my SQL", "review the SQL diff", "lint the SQL", "check my SQL changes", "SQL pre-commit check", "audit my stored proc", or asks about SQL antipatterns in a diff — even if they don't name the skill. Distinct from code-review (general review) — this carries SQL-specific incident patterns.
Pre-commit SQL code review for uncommitted database changes.
As a process F 58/100 · Will not run — References files that are not bundled: ../code-review/SKILL.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: ../code-review/SKILL.md
Process rating: all ten parameters 58/100
- 0Tools and files. 1 referenced file(s) missing: ../code-review/SKILL.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4711 tokens
- 85Steps. 94 steps, 1 vague phrases
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 (20 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 846: 120–800 characters recommended
- -213 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 19 headings
- +3Step-by-step instructions: 94 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.