Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alirezarezvani/adversarial-reviewer
Adversarial code review that breaks the self-review monoculture.
Passed 19 of 25 test cases with the skill, and 10 of 25 without it.
and 8 more in the full report
10 fixed9 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
An unhandled promise rejection was classified as a WARNING by Saboteur and as a WARNING by Security Auditor. What severity tier should it receive in the merged report?
| Checked | Without skill | With skill |
|---|---|---|
| Promotes the finding from WARNING to CRITICAL severity when flagged by multiple personas. | Missed | Passed |
The instructions your model reads when the skill loads.
Adversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no "LGTM" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.
/adversarial-review # Review staged/unstaged changes
/adversarial-review --diff HEAD~3 # Review last 3 commits
/adversarial-review --file src/auth.ts # Review a specific file
/adversarial-review --diff main...HEAD
Produces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK/CONCERNS/CLEAN verdict.
When Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces "Looks good to me" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.
This skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of "bad code."
test cases passed, vs 10 / 25 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.