AA mergeguard
Review AI-generated code before merge. Use when the user asks to review a PR, diff, branch, patch, coding-agent output, generated code, local changes, or wants a merge/no-merge recommendation. Works with GitHub PRs, local repository diffs, pasted patches, file snippets, or agent summaries. Produces a strict decision covering correctness, scope creep, security/privacy, dependency/config risk, missing tests, validation evidence, and concrete required fixes.
As a process A 84/100 · Runs to the end — weak spots: 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 84/100
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 34 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1019 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)
- +2Single-language instructions
- +3Description length 459: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 34 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.