AB code-reviewer
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.
As a process B 66/100 · Nearly there — weak spots: when it triggers, 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (code-reviewer) differs from the folder (adversarial-code-reviewer)
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 84 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Execution cost. Instruction body is 2897 tokens
- 100Progress reporting. Reports progress
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 939: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 18 headings
- +3Step-by-step instructions: 84 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.